E-commerce has revolutionized retail, yet its traditional workflows remain inefficient, with significant resource costs tied to product design and inventory. This paper introduces a novel system deployed at Alibaba that uses AI-generated items (AIGI) to address these challenges with personalized text-to-image generation for e-commerce product design. AIGI enables an innovative business mode called "sell it before you make it", where merchants can design fashion items and generate photorealistic images with digital models based on textual descriptions. Only when the items have received a certain number of orders, do the merchants start to produce them, which largely reduces reliance on physical prototypes and thus accelerates time to market. For such a promising application, we identify the underlying key scientific challenge, i.e., capturing users' group-level personalized preferences towards multiple generated images. To this end, we propose a Personalized Group-Level Preference Alignment Framework for Diffusion Models (PerFusion). We first design PerFusion Reward Model for user preference estimation with a feature-crossing-based personalized plug-in. Then we develop PerFusion with a personalized adaptive network to model diverse preferences across users, and meanwhile derive the group-level preference optimization objective to model comparative behaviors among multiple images. Both offline and online experiments demonstrate the effectiveness of our proposed algorithm. The AI-generated items achieve over 13% relative improvements for both click-through rate and conversion rate, as well as 7.9% decrease in return rate, compared to their human-designed counterparts, validating the transformative potential of AIGI for e-commerce platforms.

Recently, large language models (LLMs) have advanced recommendation systems (RSs), and recent works have begun to explore how to integrate LLMs into industrial RSs. While most approaches deploy LLMs offline to generate and pre-cache augmented representations for RSs, high-dimensional representations from LLMs introduce substantial storage and computational costs. Thus, it is crucial to compress LLM representations effectively. However, we identify a counterintuitive phenomenon during representation compression: Mid-layer Representation Advantage (MRA), where representations from middle layers of LLMs outperform those from final layers in recommendation tasks. This degraded final layer renders existing compression methods, which typically compress on the final layer, suboptimal. We interpret this based on modularity theory that LLMs develop spontaneous internal functional modularity and force the final layer to specialize in the proxy training task. Thus, we propose Modular Representation Compression (MARC) to explicitly control the modularity of LLMs. First, Modular Adjustment explicitly introduces compression and task adaptation modules, enabling the LLM to operate strictly as a representation-learning module. Next, to ground each module to its specific task, Modular Task Decoupling uses information constraints and different network structures to decouple tasks. Extensive experiments validate that MARC addresses MRA and produces efficient representations. Notably, MARC achieved a 2.82% eCPM lift in an online A/B test within a large-scale commercial search advertising scenario.

The rapid advancement of multimodal large language models has enabled agents to operate mobile devices by directly interacting with graphical user interfaces, opening new possibilities for mobile automation. However, real-world mobile tasks are often complex and allow for multiple valid solutions. This contradicts current mobile agent evaluation standards: offline static benchmarks can only validate a single predefined ''golden path'', while online dynamic testing is constrained by the complexity and non-reproducibility of real devices, making both approaches inadequate for comprehensively assessing agent capabilities. To bridge the gap between offline and online evaluation and enhance testing stability, this paper introduces a novel graph-structured benchmarking framework. By modeling the finite states observed during real-device interactions, it achieves static simulation of dynamic behaviors. Building on this, we develop ColorBench, a benchmark focused on complex long-horizon tasks. It supports evaluation of multiple valid solutions, subtask completion rate statistics, and atomic-level capability analysis. ColorBench contains 175 tasks (74 single-app, 101 cross-app) with an average length of over 13 steps. Each task includes at least two correct paths and several typical error paths, enabling quasi-dynamic interaction.

In an era dominated by information overload, effective recommender systems are essential for managing the deluge of data across digital platforms. Multi-stage cascade ranking systems are widely used in the industry, with retrieval and ranking being two typical stages. Retrieval methods sift through vast candidates to filter out irrelevant items, while ranking methods prioritize these candidates to present the most relevant items to users. Unlike studies focusing on the ranking stage, this survey explores the critical yet often overlooked retrieval stage of recommender systems. To achieve precise and efficient personalized retrieval, we summarize existing work in three key areas: improving similarity computation between user and item, enhancing indexing mechanisms for efficient retrieval, and optimizing training methods of retrieval. We also provide a comprehensive set of benchmarking experiments on three public datasets. Furthermore, we highlight current industrial applications through a case study on retrieval practices at a specific company, covering the entire retrieval process and online serving, along with practical implications and challenges. By detailing the retrieval stage, which is fundamental for effective recommendation, this survey aims to bridge the existing knowledge gap and serve as a cornerstone for researchers interested in optimizing this critical component of cascade recommender systems.

As large language models (LLMs) achieve remarkable success in natural language processing (NLP) domains, LLM-enhanced recommender systems have received much attention and are being actively explored currently. In this article, we focus on adapting and enhancing large language models for recommendation tasks. First and foremost, we identify and formulate the lifelong sequential behavior incomprehension problem for LLMs in recommendation realms, i.e., LLMs fail to effectively extract useful information from a pure textual context of long user behavior sequence, even if the length of context is well below the context limitation of LLMs. To address such an issue and improve the recommendation performance of LLMs, we propose a novel framework, namely, R etrieval- e nhanced L arge La nguage models Plus (ReLLaX), which provides full-stack optimization from three perspectives, i.e., data, prompt, and parameter. For data-level enhancement, we design semantic user behavior retrieval (SUBR) to reduce the heterogeneity of the behavior sequence, thus lowering the difficulty for LLMs to extract the essential information from user behavior sequences. Although SUBR can improve the data quality, further increase in the sequence length will still raise its heterogeneity to a level where LLMs can no longer comprehend it. Hence, we further propose to perform prompt-level and parameter-level enhancement, with the integration of conventional recommendation models (CRMs). As for prompt-level enhancement, we apply soft prompt augmentation (SPA) to explicitly inject collaborative knowledge from CRMs into the prompt. The item representations of LLMs are thus more aligned with recommendation, helping LLMs better explore the item relationships in the sequence and facilitating comprehension. Finally, for parameter-level enhancement, we propose component fully-interactive LoRA (CFLoRA). By enabling sufficient interaction between the LoRA atom components, the expressive ability of LoRA is extended, making the parameters effectively capture more sequence information. Moreover, we present new perspectives to compare current LoRA-based LLM4Rec methods, i.e., from both a composite and a decomposed view. We theoretically demonstrate that the ways they employ LoRA for recommendation are degraded versions of our CFLoRA, with different constraints on atom component interactions. Extensive experiments are conducted on three real-world public datasets to demonstrate the superiority of ReLLaX compared with existing baseline models, as well as its capability to alleviate lifelong sequential behavior incomprehension. Our code is available. 1

Recommender system plays a pervasive role in today’s online services, yet its closed-loop nature, i.e., training and deploying within a specific closed domain, constrains its access to open-world knowledge. Recently, the emergence of large language models (LLMs) has shown promise in bridging this gap by encoding extensive world knowledge and demonstrating advanced reasoning capabilities. However, previous attempts to directly implement LLMs as recommenders fall short in meeting the demanding requirements of industrial recommender systems, particularly in terms of online inference latency and offline resource efficiency. In this work, we propose an Open-World R ecommendation Framework with E fficient and Deployable K nowledge I nfusion from Large Language Models, dubbed REKI , to acquire two types of external knowledge about users and items from LLMs. Specifically, we introduce factorization prompting to elicit accurate knowledge reasoning on user preferences and items. With factorization prompting, we develop individual knowledge extraction and collective knowledge extraction tailored for different scales of recommendation scenarios, effectively reducing offline resource consumption. Subsequently, the generated user and item knowledge undergoes efficient transformation and condensation into augmented vectors through a hybridized expert-integrated network , ensuring its compatibility with the recommendation task. The obtained vectors can then be directly used to enhance the performance of any conventional recommendation model. We also ensure efficient inference by preprocessing and prestoring the knowledge from the LLM. Extensive experiments demonstrate that REKI significantly outperforms the state-of-the-art baselines and is compatible with a diverse array of recommendation algorithms and tasks. Now, REKI has been deployed to Huawei’s news and music recommendation platforms and gained a 7% and 1.99% improvement during the online A/B test.

Cognitive diagnosis (CD) plays a crucial role in intelligent education, evaluating students' comprehension of knowledge concepts based on their test histories. However, current CD methods often model students, exercises, and knowledge concepts solely on their ID relationships, neglecting the abundant semantic relationships present within the educational data space. Furthermore, contemporary intelligent tutoring systems (ITS) frequently involve the addition of new students and exercises, creating cold-start scenarios that ID-based methods find challenging to manage effectively. The advent of large language models (LLMs) offers the potential for overcoming this challenge with open-world knowledge. In this paper, we propose LLM4CD, which Leverages Large Language Models for open-world knowledge Augmented Cognitive Diagnosis. Our method utilizes the open-world knowledge of LLMs to construct cognitively expressive textual representations, which are then encoded to introduce rich semantic information into the CD task. Additionally, we propose an innovative bi-level encoder framework that models students' test histories through two levels of encoders: a macro-level cognitive text encoder and a micro-level knowledge state encoder. This approach substitutes traditional ID embeddings with semantic representations, enabling the model to accommodate new students and exercises with open-world knowledge and address the cold-start problem. Extensive experimental results demonstrate that LLM4CD consistently outperforms previous CD models on multiple real-world datasets, validating the effectiveness of leveraging LLMs to introduce rich semantic information into the CD task.

Recommender systems (RSs) have become essential for alleviating information overload and matching users with relevant content.Traditionally, RSs have focused on personalized content distribution, leveraging user interaction data and various features to rank and recommend existing items.Recently, diffusion models (DMs) have emerged as powerful generative paradigms, introducing new possibilities for RSs to not only enhance their performance for content distribution but also extend their capability boundaries to personalized content creation.On the one hand, DMs enhance the recommendation performance by mitigating challenges such as sparse user-item interactions, weak latent representations, and noisy data.On the other hand, DMs enable personalized content creation, transforming RSs from passive distributors into active generators of user-specific media assets, such as customized images, posters, and multimedia content.Given such a transformative paradigm shift, this survey provides a comprehensive review of the integration of diffusion models into recommender systems, exploring key methodologies, application scenarios, and their impact on recommendation effectiveness, diversity, and personalization.We categorize DM-based recommendation paradigms into content distribution and content creation, compare integration strategies, and discuss open challenges and future directions.This work aims to guide researchers and practitioners in developing the next generation of generative AI-powered recommendation solutions.

Graph neural networks (GNNs) have emerged as state-of-the-art methods to learn from graph-structured data for recommendation. However, most existing GNN-based recommendation methods focus on the optimization of model structures and learning strategies based on pre-defined graphs, neglecting the importance of the graph construction stage. Earlier works for graph construction usually rely on specific rules or crowdsourcing, which are either too simplistic or too labor-intensive. Recent works start to utilize large language models (LLMs) to automate the graph construction, in view of their abundant open-world knowledge and remarkable reasoning capabilities. Nevertheless, they generally suffer from two limitations: (1) invisibility of global view (e.g., overlooking contextual information) and (2) construction inefficiency. To this end, we introduce AutoGraph, an automatic graph construction framework based on LLMs for recommendation. Specifically, we first use LLMs to infer the user preference and item knowledge, which is encoded as semantic vectors. Next, we employ vector quantization to extract the latent factors from the semantic vectors. The latent factors are then incorporated as extra nodes to link the user/item nodes, resulting in a graph with in-depth global-view semantics. We further design metapath-based message aggregation to effectively aggregate the semantic and collaborative information. The framework is model-agnostic and compatible with different backbone models. Extensive experiments on three real-world datasets demonstrate the efficacy and efficiency of AutoGraph compared to existing baseline methods. We have deployed AutoGraph in Huawei advertising platform, and gain a 2.69% improvement on RPM and a 7.31% improvement on eCPM in the online A/B test. Currently AutoGraph has been used as the main traffic model, serving hundreds of millions of people.

Recommender systems (RSs) often suffer from the feedback loop phenomenon, i.e., RSs are trained on data biased by their recommendations. This leads to the filter bubble effect that reinforces homogeneous content and reduces user satisfaction. To this end, serendipity recommendations, which offer unexpected yet relevant items, are proposed. Recently, large language models (LLMs) have shown potential in serendipity prediction due to their extensive world knowledge and reasoning capabilities. However, they still face challenges in aligning serendipity judgments with human assessments, handling long user behavior sequences, and meeting the latency requirements of industrial RSs. To address these issues, we propose SERAL (Serendipity Recommendations with Aligned Large Language Models), a framework comprising three stages: (1) Cognition Profile Generation to compress user behavior into multi-level profiles; (2) SerenGPT Alignment to align serendipity judgments with human preferences using enriched training data; and (3) Nearline Adaptation to integrate SerenGPT into industrial RSs pipelines efficiently. Online experiments demonstrate that SERAL improves exposure ratio (PVR), clicks, and transactions of serendipitous items by 5.7%, 29.56%, and 27.6%, enhancing user experience without much impact on overall revenue. Now, it has been fully deployed in ''Guess What You Like'' on the Taobao App homepage.

Interactive recommender systems (IRSs) aim to meet user needs through natural language dialogues, optimizing recommendations with minimal interactions. Typically, IRSs are based on large language models (LLMs). Existing methods generally consist of two stages: decision-making (deciding whether to recommend or ask clarification questions) and action execution (generating recommendations or clarification questions). These methods usually follow a decision-first paradigm, where the model first decides on the action based on past conversations, and then executes the corresponding action. Since LLMs struggle to process a large number of candidate items, the recommendation process is often carried out in collaboration with external recommendation tools, which provide a small candidate set for LLMs to refine.

The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers, generating augmented knowledge for downstream tasks. However, in recommendation scenarios with numerous users and items, even offline knowledge generation with LLMs demands significant time and computational resources. This inefficiency arises from the autoregressive nature of LLMs. A promising solution is speculative decoding, a Draft-Then-Verify approach that increases the number of tokens generated per decoding step. In this work, we first identify recommendation knowledge generation as a highly fitting use case for retrieval-based speculative decoding. Then, we discern its two characteristics: (1) the vast number of items and users in RSs leads to retrieval inefficiency, and (2) RSs exhibit high diversity tolerance for LLM-generated text. Building on these insights, we introduce Lossless Acceleration via Speculative Decoding for LLM-based Recommender Systems (LASER), which features a Customized Retrieval Pool to enhance retrieval efficiency and Relaxed Verification to improve the acceptance rate of draft tokens. LASER achieves a 3-5x speedup on public datasets and saves about 67% of computational resources during the online A/B test on a large-scale advertising scenario with lossless downstream recommendation performance. Our code is available at https://github.com/YunjiaXi/LASER

Recommender systems (RS) are pivotal in managing information overload in modern digital services. A key challenge in RS is efficiently processing vast item pools to deliver highly personalized recommendations under strict latency constraints. Multi-stage cascade ranking addresses this by employing computationally efficient retrieval methods to cover diverse user interests, followed by more precise ranking models to refine the results. In the retrieval stage, multi-channel retrieval is often used to generate distinct item subsets from different candidate generators, leveraging the complementary strengths of these methods to maximize coverage. However, forwarding all retrieved items overwhelms downstream rankers, necessitating truncation. Despite advancements in individual retrieval methods, multi-channel fusion, the process of efficiently merging multi-channel retrieval results, remains underexplored. We are the first to identify and systematically investigate multi-channel fusion in the retrieval stage. Current industry practices often rely on heuristic approaches and manual designs, which often lead to suboptimal performance. Moreover, traditional gradient-based methods like SGD are unsuitable for this task due to the non-differentiable nature of the selection process. In this paper, we explore advanced channel fusion strategies by assigning systematically optimized weights to each channel. We utilize black-box optimization techniques, including the Cross Entropy Method and Bayesian Optimization for global weight optimization, alongside policy gradient-based approaches for personalized merging. Our methods enhance both personalization and flexibility, achieving significant performance improvements across multiple datasets and yielding substantial gains in real-world deployments, offering a scalable solution for optimizing multi-channel fusion in retrieval.

A question-answering (QA) simulator is a model that simulates human students QA behaviors. By leveraging QA history to estimate the probability of correctly answering a newly recommended question, the simulator enables the educational recommender systems to be trained in a simulated environment, protecting human students from the potential negative impact of low-quality recommendations. Despite its significant importance, the construction of QA simulators has not been thoroughly explored in the research domain of AI. Previous methods mainly rely on existing knowledge tracing (KT) models to construct such a simulator. However, due to the discrepancy between the KT task and the simulation task, those KT-based simulators suffer from severe bias accumulation, which limits the effectiveness of the simulation. In this paper, we propose a method called Diffusion-based Simulator (DSim), which takes advantage of diffusion to alleviate the bias accumulation. To our knowledge, DSim is the first to focus on building a QA simulator.

A vast amount of user behavior data is constantly accumulating on today's large recommendation platforms, recording users' various interests and tastes. Preserving knowledge from the old data while new data continually arrives is a vital problem for recommender systems. Existing approaches generally seek to save the knowledge implicitly in the model parameters. However, such a parameter-centric approach lacks scalability and flexibility---the capacity is hard to scale, and the knowledge is inflexible to utilize. Hence, in this work, we propose a framework that turns massive user behavior data to retrievable knowledge (D2K). It is a data-centric approach that is model-agnostic and easy to scale up. Different from only storing unary knowledge such as the user-side or item-side information, D2K propose to store ternary knowledge for recommendation, which is determined by the complete recommendation factors---user, item, and context. The knowledge retrieved by target samples can be directly used to enhance the performance of any recommendation algorithms. Specifically, we introduce a Transformer-based knowledge encoder to transform the old data into knowledge with the user-item-context cross features. A personalized knowledge adaptation unit is devised to effectively exploit the information from the knowledge base by adapting the retrieved knowledge to the target samples. Extensive experiments demonstrate the superiority of the proposed method.

With the rapid development of online services and web applications, recommender systems (RS) have become increasingly indispensable for mitigating information overload and matching users’ information needs by providing personalized suggestions over items. Although the RS research community has made remarkable progress over the past decades, conventional recommendation models (CRM) still have some limitations, e.g., lacking open-domain world knowledge, and difficulties in comprehending users’ underlying preferences and motivations. Meanwhile, large language models (LLM) have shown impressive general intelligence and human-like capabilities for various natural language processing (NLP) tasks, which mainly stem from their extensive open-world knowledge, logical and commonsense reasoning abilities, as well as their comprehension of human culture and society. Consequently, the emergence of LLM is inspiring the design of RS and pointing out a promising research direction, i.e., whether we can incorporate LLM and benefit from their common knowledge and capabilities to compensate for the limitations of CRM. In this article, we conduct a comprehensive survey on this research direction, and draw a bird’s-eye view from the perspective of the whole pipeline in real-world RS. Specifically, we summarize existing research works from two orthogonal aspects: where and how to adapt LLM to RS. For the “ WHERE ” question, we discuss the roles that LLM could play in different stages of the recommendation pipeline, i.e., feature engineering, feature encoder, scoring/ranking function, user interaction, and pipeline controller. For the “ HOW ” question, we investigate the training and inference strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to tune LLM or not during training, and whether to involve CRM for inference. Detailed analysis and general development paths are provided for both “WHERE” and “HOW” questions, respectively. Then, we highlight the key challenges in adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and ethics. Finally, we summarize the survey and discuss the future prospects.

With the development of multimedia systems, multimodal recommendations are playing an essential role, as they can leverage rich contexts beyond interactions. Existing methods mainly regard multimodal information as an auxiliary, using them to help learn ID features; However, there exist semantic gaps among multimodal content features and ID-based features, for which directly using multimodal information as an auxiliary would lead to misalignment in representations of users and items. In this paper, we first systematically investigate the misalignment issue in multimodal recommendations, and propose a solution named AlignRec. In AlignRec, the recommendation objective is decomposed into three alignments, namely alignment within contents, alignment between content and categorical ID, and alignment between users and items. Each alignment is characterized by a specific objective function and is integrated into our multimodal recommendation framework. To effectively train AlignRec, we propose starting from pre-training the first alignment to obtain unified multimodal features and subsequently training the following two alignments together with these features as input. As it is essential to analyze whether each multimodal feature helps in training and accelerate the iteration cycle of recommendation models, we design three new classes of metrics to evaluate intermediate performance. Our extensive experiments on three real-world datasets consistently verify the superiority of AlignRec compared to nine baselines. We also find that the multimodal features generated by AlignRec are better than currently used ones, which are to be open-sourced in our repository https://github.com/sjtulyf123/AlignRec_CIKM24.

Large language models have been flourishing in the natural language processing (NLP) domain, and their potential for recommendation has been paid much attention to. Despite the intelligence shown by the recommendation-oriented finetuned models, LLMs struggle to fully understand the user behavior patterns due to their innate weakness in interpreting numerical features and the overhead for long context, where the temporal relations among user behaviors, subtle quantitative signals among different ratings, and various side features of items are not well explored. Existing works only fine-tune a sole LLM on given text data without introducing that important information to it, leaving these problems unsolved. In this paper, we propose ELCoRec to Enhance Language understanding with Co-Propagation of numerical and categorical features for Recommendation. Concretely, we propose to inject the preference understanding capability into LLM via a GAT expert model where the user preference is better encoded by parallelly propagating the temporal relations, and rating signals as well as various side information of historical items. The parallel propagation mechanism could stabilize heterogeneous features and offer an informative user preference encoding, which is then injected into the language models via soft prompting at the cost of a single token embedding. To further obtain the user's recent interests, we proposed a novel Recent interaction Augmented Prompt (RAP) template. Experiment results over three datasets against strong baselines validate the effectiveness of ELCoRec.

Knowledge Tracing (KT) aims to determine whether students will respond correctly to the next question, which is a crucial task in intelligent tutoring systems (ITS). In educational KT scenarios, transductive ID-based methods often face severe data sparsity and cold start problems, where interactions between individual students and questions are sparse, and new questions and concepts consistently arrive in the database. In addition, existing KT models only implicitly consider the correlation between concepts and questions, lacking direct modeling of the more complex relationships in the heterogeneous graph of concepts and questions. In this paper, we propose a Structure-aware INductive Knowledge Tracing model with large language model (dubbed SINKT), which, for the first time, introduces large language models (LLMs) and realizes inductive knowledge tracing. Firstly, SINKT utilizes LLMs to introduce structural relationships between concepts and constructs a hetero- geneous graph for concepts and questions. Secondly, by encoding concepts and questions with LLMs, SINKT incorporates semantic information to aid prediction. Finally, SINKT predicts the student's response to the target question by interacting with the student's knowledge state and the question representation. Experiments on four real-world datasets demonstrate that SINKT achieves state-of-the-art performance among 12 existing transductive KT models. Additionally, we explore the performance of SINKT on the inductive KT task and provide insights into various modules.

Conversational recommender systems (CRSs) aim to capture user preferences and provide personalized recommendations through multi-round natural language dialogues. However, most existing CRS models mainly focus on dialogue comprehension and preferences mining from the current dialogue session, overlooking user preferences in historical dialogue sessions. The preferences embedded in historical sessions and the current session exhibit continuity and sequentiality, and we refer to such CRSs as sequential CRSs. In this work, we leverage memory-enhanced LLMs to model the preference continuity, addressing two key issues: (1) redundancy and noise in historical dialogue sessions, and (2) the cold-start users problem. Thus, we propose a Memory-enhanced Conversational Recommender System Framework with Large Language Models (dubbed MemoCRS), consisting of user-specific memory and general memory. User-specific memory is tailored to each user's interests and uses an entity-based memory bank to refine preferences and retrieve relevant memory, thereby reducing the redundancy and noise of historical sessions. The general memory, encapsulating collaborative knowledge and reasoning guidelines, can provide shared knowledge for users, especially cold-start users. With the above memory, LLMs are empowered to deliver more precise and tailored recommendations for each user. Extensive experiments on Chinese and English datasets demonstrate MemoCRS's effectiveness.

Educational recommendation seeks to suggest knowledge concepts that match a learner's ability, thus facilitating a personalized learning experience. In recent years, reinforcement learning (RL) methods have achieved considerable results by taking the encoding of the learner's exercise log as the state and employing an RL-based agent to make suitable recommendations. However, these approaches suffer from handling the diverse and dynamic learner's knowledge states. In this paper, we introduce the privileged feature distillation technique and propose the P rivileged K nowledge S tate D istillation (PKSD ) framework, allowing the RL agent to leverage the "actual'' knowledge state as privileged information in the state encoding to help tailor recommendations to meet individual needs. Concretely, our PKSD takes the privileged knowledge states together with the representations of the exercise log for the state representations during training. And through distillation, we transfer the ability to adapt to learners to aknowledge state adapter. During inference, theknowledge state adapter would serve as the estimated privileged knowledge states instead of the real one since it is not accessible. Considering that there are strong connections among the knowledge concepts in education, we further propose to collaborate the graph structure learning for concepts into our PKSD framework. This new approach is termed GEPKSD (Graph-Enhanced PKSD). As our method is model-agnostic, we evaluate PKSD and GEPKSD by integrating them with five different RL bases on four public simulators, respectively. Our results verify that PKSD can consistently improve the recommendation performance with various RL methods, and our GEPKSD could further enhance the effectiveness of PKSD in all the simulations.

Click-through rate (CTR) prediction plays as a core function module in various personalized online services. The traditional ID-based models for CTR prediction take as inputs the one-hot encoded ID features of tabular modality, which capture the collaborative signals via feature interaction modeling. But the one-hot encoding discards the semantic information included in the textual features. Recently, the emergence of Pretrained Language Models (PLMs) has given rise to another paradigm, which takes as inputs the sentences of textual modality obtained by hard prompt templates and adopts PLMs to extract the semantic knowledge. However, PLMs often face challenges in capturing field-wise collaborative signals and distinguishing features with subtle textual differences. In this paper, to leverage the benefits of both paradigms and meanwhile overcome their limitations, we propose to conduct Fine-grained feature-level ALignment between ID-based Models and Pretrained Language Models (FLIP) for CTR prediction. Unlike most methods that solely rely on global views through instance-level contrastive learning, we design a novel jointly masked tabular/language modeling task to learn fine-grained alignment between tabular IDs and word tokens. Specifically, the masked data of one modality (i.e., IDs and tokens) has to be recovered with the help of the other modality, which establishes the feature-level interaction and alignment via sufficient mutual information extraction between dual modalities. Moreover, we propose to jointly finetune the ID-based model and PLM by adaptively combining the output of both models, thus achieving superior performance in downstream CTR prediction tasks. Extensive experiments on three real-world datasets demonstrate that FLIP outperforms SOTA baselines, and is highly compatible with various ID-based models and PLMs. The code is available12.

Recommender system plays a vital role in various online services. However, its insulated nature of training and deploying separately within a specific closed domain limits its access to open-world knowledge. Recently, the emergence of large language models (LLMs) has shown promise in bridging this gap by encoding extensive world knowledge and demonstrating reasoning capabilities. Nevertheless, previous attempts to directly use LLMs as recommenders cannot meet the inference latency demand of industrial recommender systems. In this work, we propose an Open-World Knowledge Augmented Recommendation Framework with Large Language Models, dubbed KAR, to acquire two types of external knowledge from LLMs — the reasoning knowledge on user preferences and the factual knowledge on items. We introduce factorization prompting to elicit accurate reasoning on user preferences. The generated reasoning and factual knowledge are effectively transformed and condensed into augmented vectors by a hybrid-expert adaptor in order to be compatible with the recommendation task. The obtained vectors can then be directly used to enhance the performance of any recommendation model. We also ensure efficient inference by preprocessing and prestoring the knowledge from the LLM. Extensive experiments show that KAR significantly outperforms the state-of-the-art baselines and is compatible with a wide range of recommendation algorithms. We deploy KAR to Huawei’s news and music recommendation platforms and gain a 7% and 1.7% improvement in the online A/B test, respectively.

Several large language model (LLM) agents have been constructed for diverse purposes such as web navigation and online shopping, leveraging the broad knowledge and text comprehension capabilities of LLMs. Many of these works rely on in-context examples to achieve generalization without requiring fine-tuning. However, few have addressed the challenge of selecting and effectively utilizing these examples. Recent approaches have introduced trajectory-level retrieval with task meta-data and the use of trajectories as in-context examples to enhance overall performance in some sequential decision making tasks like computer control. Nevertheless, these methods face issues like plausible examples retrieved without task-specific state transition dynamics and long input with plenty of irrelevant context due to using complete trajectories. In this paper, we propose a novel framework (TRAD) to tackle these problems. TRAD first employs Thought Retrieval for step-level demonstration selection through thought matching, enhancing the quality of demonstrations and reducing irrelevant input noise. Then, Aligned Decision is introduced to complement retrieved demonstration steps with their preceding or subsequent steps, providing tolerance for imperfect thought and offering a balance between more context and less noise. Extensive experiments on ALFWorld and Mind2Web benchmarks demonstrate that TRAD not only surpasses state-of-the-art models but also effectively reduces noise and promotes generalization. Furthermore, TRAD has been deployed in real-world scenarios of a global business insurance company and yields an improved success rate of robotic process automation. Our codes are available at: https://github.com/skyriver-2000/TRAD-Official.

Ranking items regarding individual user interests is a core technique of multiple downstream tasks such as recommender systems. Learning such a personalized ranker typically relies on the implicit feedback from users' past click-through behaviors. However, collected feedback is biased toward previously highly-ranked items and directly learning from it would result in "rich-get-richer" phenomena. In this paper, we propose a simple yet sufficient unbiased learning-to-rank paradigm named InfoRank that aims to simultaneously address both position and popularity biases. We begin by consolidating the impacts of those biases into a single observation factor, thereby providing a unified approach to addressing bias-related issues. Subsequently, we minimize the mutual information between the observation estimation and the relevance estimation conditioned on the input features. By doing so, our relevance estimation can be proved to be free of bias. To implement InfoRank, we first incorporate an attention mechanism to capture latent correlations within user-item features, thereby generating estimations of observation and relevance. We then introduce a regularization term, grounded in conditional mutual information, to promote conditional independence between relevance estimation and observation estimation. Experimental evaluations conducted across three extensive recommendation and search datasets reveal that InfoRank learns more precise and unbiased ranking strategies.

Click-through rate (CTR) prediction has become increasingly indispensable for various Internet applications. Traditional CTR models convert the multi-field categorical data into ID features via one-hot encoding, and extract the collaborative signals among features. Such a paradigm suffers from the problem of semantic information loss. Another line of research explores the potential of pretrained language models (PLMs) for CTR prediction by converting input data into textual sentences through hard prompt templates. Although semantic signals are preserved, they generally fail to capture the collaborative information (e.g., feature interactions, pure ID features), not to mention the unacceptable inference overhead brought by the huge model size. In this paper, we aim to model both the semantic knowledge and collaborative knowledge for accurate CTR estimation, and meanwhile address the inference inefficiency issue. To benefit from both worlds and close their gaps, we propose a novel model-agnostic framework (i.e., ClickPrompt), where we incorporate CTR models to generate interaction-aware soft prompts for PLMs. We design a prompt-augmented masked language modeling (PA-MLM) pretraining task, where PLM has to recover the masked tokens based on the language context, as well as the soft prompts generated by CTR model. The collaborative and semantic knowledge from ID and textual features would be explicitly aligned and interacted via the prompt interface. Then, we can either tune the CTR model with PLM for superior performance, or solely tune the CTR model without PLM for inference efficiency. Experiments on four real-world datasets validate the effectiveness of ClickPrompt compared with existing baselines.

With large language models (LLMs) achieving remarkable breakthroughs in NLP domains, LLM-enhanced recommender systems have received much attention and have been actively explored currently. In this paper, we focus on adapting and empowering a pure large language model for zero-shot and few-shot recommendation tasks. First and foremost, we identify and formulate the lifelong sequential behavior incomprehension problem for LLMs in recommendation domains, i.e., LLMs fail to extract useful information from a textual context of long user behavior sequence, even if the length of context is far from reaching the context limitation of LLMs. To address such an issue and improve the recommendation performance of LLMs, we propose a novel framework, namely Retrieval enhanced Large Language models (ReLLa) for recommendation tasks in both zero-shot and few-shot settings. For zero-shot recommendation, we perform semantic user behavior retrieval (SUBR) to improve the data quality of testing samples, which greatly reduces the difficulty for LLMs to extract the essential knowledge from user behavior sequences. As for few-shot recommendation, we further design retrieval-enhanced instruction tuning (ReiT) by adopting SUBR as a data augmentation technique for training samples. Specifically, we develop a mixed training dataset consisting of both the original data samples and their retrieval-enhanced counterparts. We conduct extensive experiments on three real-world public datasets to demonstrate the superiority of ReLLa compared with existing baseline models, as well as its capability for lifelong sequential behavior comprehension. To be highlighted, with only less than 10% training samples, few-shot ReLLa can outperform traditional CTR models that are trained on the entire training set (e.g., DCNv2, DIN, SIM).

We primarily focus on the field of multi-scenario recommendation, which poses a significant challenge in effectively leveraging data from different scenarios to enhance predictions in scenarios with limited data. Current mainstream efforts mainly center around innovative model network architectures, with the aim of enabling the network to implicitly acquire knowledge from diverse scenarios. However, the uncertainty of implicit learning in networks arises from the absence of explicit modeling, leading to not only difficulty in training but also incomplete user representation and suboptimal performance. Furthermore, through causal graph analysis, we have discovered that the scenario itself directly influences click behavior, yet existing approaches directly incorporate data from other scenarios during the training of the current scenario, leading to prediction biases when they directly utilize click behaviors from other scenarios to train models. To address these problems, we propose the Multi-Scenario Causal-driven Adaptive Network M-scan). This model incorporates a Scenario-Aware Co-Attention mechanism that explicitly extracts user interests from other scenarios that align with the current scenario. Additionally, it employs a Scenario Bias Eliminator module utilizing causal counterfactual inference to mitigate biases introduced by data from other scenarios. Extensive experiments on two public datasets demonstrate the efficacy of our M-scan compared to the existing baseline models.

Real-Time Bidding (RTB) is one of the most important forms of online advertising, where an auction is hosted in real time to sell the individual ad impression. How to design an automated bidding strategy in response to the dynamic auction environment is crucial for improving user experience, protecting the interests of advertisers, and promoting the long-term development of the advertising platform. As an exciting topic in the real-world industry, it has attracted great research interest from several disciplines, most notably data science. There have been abundant studies on bidding strategy design which are based on the large volume of historical ad requests. Despite its popularity and significance, few works provide a summary for bid optimization. In this survey, we present the latest overview of the recent works to shed light on the optimization techniques where most of them are validated in practice. We first explore the optimization problem in different works, explaining how these different settings affect the bidding strategy designs. Then, some forms of bidding functions and specific optimization techniques are illustrated. Further, we specifically discuss a new trend about bidding in first-price auctions, which have gradually become popular in recent years. From this survey, both practitioners and researchers can gain insights of the challenges and future prospects of bid optimization in RTB.

As a critical task for large-scale commercial recommender systems, reranking rearranges items in the initial ranking lists from the previous ranking stage to better meet users’ demands. Foundational work in reranking has shown the potential of improving recommendation results by uncovering mutual influence among items. However, rather than considering the context of initial lists as most existing methods do, an ideal reranking algorithm should consider the counterfactual context— the position and the alignment of the items in the reranked lists . In this work, we propose a novel pairwise reranking framework, Utility-oriented Reranking with Counterfactual Context (URCC), which maximizes the overall utility after reranking efficiently. Specifically, we first design a utility-oriented evaluator, which applies Bi-LSTM and graph attention mechanism to estimate the listwise utility via the counterfactual context modeling. Then, under the guidance of the evaluator, we propose a pairwise reranker model to find the most suitable position for each item by swapping misplaced item pairs. Extensive experiments on two benchmark datasets and a proprietary real-world dataset demonstrate that URCC significantly outperforms the state-of-the-art models in terms of both relevance-based metrics and utility-based metrics.

Recommender systems are expected to be assistants that help human users find relevant information automatically without explicit queries. As recommender systems evolve, increasingly sophisticated learning techniques are applied and have achieved better performance in terms of user engagement metrics such as clicks and browsing time. The increase in the measured performance, however, can have two possible attributions: a better understanding of user preferences, and a more proactive ability to utilize human bounded rationality to seduce user over-consumption. A natural following question is whether current recommendation algorithms are manipulating user preferences. If so, can we measure the manipulation level? In this article, we present a general framework for benchmarking the degree of manipulations of recommendation algorithms, in both slate recommendation and sequential recommendation scenarios. The framework consists of four stages, initial preference calculation, training data collection, algorithm training and interaction, and metrics calculation that involves two proposed metrics, Manipulation Score and Preference Shift. We benchmark some representative recommendation algorithms in both synthetic and real-world datasets under the proposed framework. We have observed that a high online click-through rate does not necessarily mean a better understanding of user initial preference, but ends in prompting users to choose more documents they initially did not favor. Moreover, we find that the training data have notable impacts on the manipulation degrees, and algorithms with more powerful modeling abilities are more sensitive to such impacts. The experiments also verified the usefulness of the proposed metrics for measuring the degree of manipulations. We advocate that future recommendation algorithm studies should be treated as an optimization problem with constrained user preference manipulations.

Extending from sequential recommendation models, in this article, we present a novel framework named Search-based Time-Aware Recommendation (STARec), which first retrieves the historical behaviors of the given user through a search-based retriever and then captures the user’s evolving demands over time through a time-aware sequential network. We notice that the key insight of STARec is to use the feature and labels to augment the representations, and thus the effectiveness of STARec relies on the acquisition of rich browsing records of the target user and powerful representation of each browsed item and thus its performance could heavily drop regarding long-tail users and items. To this end, we extend STARec by constructing a graph upon the user–item interactions and leveraging the graph structure to enhance the representation learning. We call this extended version Search-based Time-Aware Graph-Enhanced Recommendation (STAGE). We conduct extensive experiments on three real-world datasets and STARec achieves consistent superiority. We further compare STAGE against STARec long-tail users and our results demonstrate that STAGE could outperform STARec at most cases. Results of online A/B tests show that STARec and STAGE achieve an average click-through rate improvement of around 6% and 1.5% in the two main item recommendation scenarios, respectively. 1

Learning-to-rank is a core technique in the top-N recommendation task, where an ideal ranker would be a mapping from an item set to an arrangement (a.k.a. permutation). Most existing solutions fall in the paradigm of probabilistic ranking principle (PRP), i.e., first score each item in the candidate set and then perform a sort operation to generate the top ranking list. However, these approaches neglect the contextual dependence among candidate items during individual scoring, and the sort operation is non-differentiable. To bypass the above issues, we propose Set-To-Arrangement Ranking (STARank), a new framework directly generates the permutations of the candidate items without the need for individually scoring and sort operations; and is end-to-end differentiable. As a result, STARank can operate when only the ground-truth permutations are accessible without requiring access to the ground-truth relevance scores for items. For this purpose, STARank first reads the candidate items in the context of the user browsing history, whose representations are fed into a Plackett-Luce module to arrange the given items into a list. To effectively utilize the given ground-truth permutations for supervising STARank, we leverage the internal consistency property of Plackett-Luce models to derive a computationally efficient list-wise loss. Experimental comparisons against 9 the state-of-the-art methods on 2 learning-to-rank benchmark datasets and 3 top-N real-world recommendation datasets demonstrate the superiority of STARank in terms of conventional ranking metrics. Notice that these ranking metrics do not consider the effects of the contextual dependence among the items in the list, we design a new family of simulation-based ranking metrics, where existing metrics can be regarded as special cases. STARank can consistently achieve better performance in terms of PBM and UBM simulation-based metrics.

Goal-oriented Learning path recommendation aims to recommend learning items (concepts or exercises) step-by-step to a learner to promote the mastery level of her specific learning goals. By formulating this task as a Markov decision process, reinforcement learning (RL) methods have demonstrated great power. Although extensive research efforts have been made, previous methods still fail to recommend effective goal-oriented paths due to the under-utilizing of goals. Specifically, it is mainly reflected in two aspects: (1)The lack of goal planning. When learners have multiple goals with different difficulties, the previous methods can't fully utilize the difficulties and dependencies between goal learning items to plan the sequence of achieving these goals, making the path chaotic and inefficient; (2)The lack of efficiency in goal achieving. When pursuing a single goal, the path may contain learning items unrelated to the goal, which makes realizing a certain goal inefficient. To address these challenges, we present a novel Graph Enhanced Hierarchical Reinforcement Learning (GEHRL) framework for goal-oriented learning path recommendation. The framework divides learning path recommendation into two parts: sub-goal selection(planning) and sub-goal achieving(learning item recommendation). Specifically, we employ a high-level agent as a sub-goal selector to select sub-goals for the low-level agent to achieve. The low-level agent in the framework is to recommend learning items to the learner. To make the path only contain goal-related learning items to improve the efficiency of achieving the goal, we develop a graph-based candidate selector to constrain the action space of the low-level agent based on the sub-goal and knowledge graph. We also develop test-based internal reward for low-level training so that the sparsity problem of external reward can be alleviated. Extensive experiments on three different simulators demonstrate our framework achieves state-of-the-art performance.

Position auctions are widely studied in the context of sponsored search advertising, where multiple ad slots are sold in a single auction. In traditional sponsored search, bids are submitted at the keyword level, while recent works have explored transitioning to impression-level bidding using Real-Time Bidding (RTB) techniques to achieve finer bidding. However, position auctions introduce varying user appeal across different positions and more dynamic auction landscape, which RTB, originally devised for single-slot display advertising, fails to address adequately.

Order execution is a fundamental task in quantitative finance, aiming at finishing acquisition or liquidation for a number of trading orders of the specific assets. Recent advance in model-free reinforcement learning (RL) provides a data-driven solution to the order execution problem. However, the existing works always optimize execution for an individual order, overlooking the practice that multiple orders are specified to execute simultaneously, resulting in suboptimality and bias. In this paper, we first present a multi-agent RL (MARL) method for multi-order execution considering practical constraints. Specifically, we treat every agent as an individual operator to trade one specific order, while keeping communicating with each other and collaborating for maximizing the overall profits. Nevertheless, the existing MARL algorithms often incorporate communication among agents by exchanging only the information of their partial observations, which is inefficient in complicated financial market. To improve collaboration, we then propose a learnable multi-round communication protocol, for the agents communicating the intended actions with each other and refining accordingly. It is optimized through a novel action value attribution method which is provably consistent with the original learning objective yet more efficient. The experiments on the data from two real-world markets have illustrated superior performance with significantly better collaboration effectiveness achieved by our method.

With the widespread application of online advertising systems, click-through rate (CTR) prediction has received more and more attention and research. The most prominent features of CTR prediction are its multi-field categorical data format, and vast and daily-growing data volume (e.g., billions of user click logs). The large capacity of neural models helps digest such massive amounts of data under the supervised learning paradigm, yet they fail to utilize the substantial data to its full potential, since click signals are not sufficient enough for the model to learn capable representations of features and instances. The self-supervised learning paradigm provides a more promising pretrain-finetune solution to better exploit the large amount of user click logs and learn more robust and effective representations. However, current works on this line are still preliminary and rudimentary, leaving self-supervised learning for CTR prediction still an open question. To this end, we propose a Model-agnostic Pretraining (MAP) framework that applies feature corruption and recovery on multi-field categorical data, and more specifically, we derive two practical algorithms: masked feature prediction (MFP) and replaced feature detection (RFD). MFP digs into feature interactions within each instance through masking and predicting a small portion of input features, and we also introduce Noise Contrastive Estimation (NCE) to handle large feature spaces. RFD further turns MFP into a binary classification mode through replacing and detecting changes in input features, making it even simpler and more effective for CTR pretraining. Our extensive experiments on two real-world million-level datasets (i.e., Avazu, Criteo) demonstrate the advantages of these two methods over several strong baselines, and achieve new state-of-the-art in terms of both performance and efficiency for CTR prediction.

Real-Time Bidding (RTB) has shown remarkable success in display advertising and has been employed in other advertising scenarios, e.g., sponsored search advertising with multiple ad slots. Many current RTB techniques built for single-slot display advertising are thus no longer applicable, especially in the bid landscape forecasting. Landscape forecasting predicts market competition, including the highest bid price and winning probability, which is preliminary and crucial for the subsequent bidding strategy design. In the multi-slot advertising, predicting the winning prices for each position requires a more precise differentiation of bids among top advertisers. Furthermore, defining the winning probability and addressing censorship issues are not as straightforward as in the case of a single slot. In view of these challenges, how to forecast the bidding landscape in the multi-slot environment remains open.

Computerized Adaptive Testing (CAT) refers to an online system that adaptively selects the best-suited question for students with various abilities based on their historical response records. Compared with traditional CAT methods based on heuristic rules, recent data-driven CAT methods obtain higher performance by learning from large-scale datasets. However, most CAT methods only focus on the quality objective of predicting the student ability accurately, but neglect concept diversity or question exposure control, which are important considerations in ensuring the performance and validity of CAT. Besides, the students' response records contain valuable relational information between questions and knowledge concepts. The previous methods ignore this relational information, resulting in the selection of sub-optimal test questions. To address these challenges, we propose a Graph-Enhanced Multi-Objective method for CAT (GMOCAT). Firstly, three objectives, namely quality, diversity and novelty, are introduced into the Scalarized Multi-Objective Reinforcement Learning framework of CAT, which respectively correspond to improving the prediction accuracy, increasing the concept diversity and reducing the question exposure. We use an Actor-Critic Recommender to select questions and optimize three objectives simultaneously by the scalarization function. Secondly, we utilize the graph neural network to learn relation-aware embeddings of questions and concepts. These embeddings are able to aggregate neighborhood information in the relation graphs between questions and concepts. We conduct experiments on three real-world educational datasets. The experimental results show that GMOCAT not only outperforms the state-of-the-art methods in the ability prediction, but also achieve superior performance in improving the concept diversity and alleviating the question exposure.

As an emerging field driven by industrial applications, integrated re-ranking combines lists from upstream sources into a single list, and presents it to the user. The quality of integrated re-ranking is especially sensitive to real-time user behaviors and preferences. However, existing methods are all built on the cloud-to-edge framework, where mixed lists are generated by the cloud model and then sent to the devices. Despite its effectiveness, such a framework fails to capture users' real-time preferences due to the network bandwidth and latency. Hence, we propose to place the integrated re-ranking model on devices, allowing for the full exploitation of real-time behaviors. To achieve this, we need to address two key issues: first, how to extract users' preferences for different sources from heterogeneous and imbalanced user behaviors; second, how to explore the correlation between the extracted personalized preferences and the candidate items. In this work, we present the first on-Device Integrated Re-ranking framework, DIR, to avoid delays in processing real-time user behaviors. DIR includes a multi-sequence behavior modeling module to extract the user's source-level preferences, and a preference-adaptive re-ranking module to incorporate personalized source-level preferences into the re-ranking of candidate items. Besides, we design exposure loss and utility loss to jointly optimize exposure fairness and overall utility. Extensive experiments on three datasets show that DIR significantly outperforms the state-of-the-art baselines in utility-based and fairness-based metrics.

Most click models focus on user behaviors towards a single list. However, with the development of user interface (UI) design, the layout of displayed items on a result page tends to be multi-block style instead of a single list, which requires different assumptions to model user behaviors more accurately. There exist click models for multi-block pages in desktop contexts, but they cannot be directly applied to mobile scenarios due to different interaction manners, result types and especially multi-block presentation styles. In particular, multi-block mobile pages can normally be decomposed into interleavings of basic vertical blocks and horizontal blocks, thus resulting in typically F-shape forms. To mitigate gaps between desktop and mobile contexts for multi-block pages, we conduct a user eye-tracking study, and identify users' sequential browsing, block skip and comparison patterns on F-shape pages. These findings lead to the design of a novel F-shape Click Model (FSCM), which serves as a general solution to multi-block mobile pages. Firstly, we construct a Directed Acyclic Graph (DAG) for each page, where each item is regarded as a vertex and each edge indicates the user's possible examination flow. Secondly, we propose DAG-structured GRUs and a comparison module to model users' sequential (sequential browsing, block skip) and non-sequential (comparison) behaviors respectively. Finally, we combine GRU states and comparison patterns to perform user click predictions. Experiments show that FSCM outperforms baseline models.

This paper is concerned with TV recommendation, where one major challenge is the coupling behavior issue that the behaviors of multiple users are coupled together and not directly distinguishable because the users share the same account. Unable to identify the current watching user and use the coupling behaviors directly could lead to sub-optimal recommendation results due to the noise introduced by the behaviors of other users. Most existing methods deal with this issue either by unsupervised clustering algorithms or depending on latent user representation learning with strong assumptions. However, they neglect to sophisticatedly model the current session behaviors, which carry the information of user identification. Another critical limitation of the existing models is the lack of supervision signal on distinguishing behaviors because they solely depend on the final click label, which is insufficient to provide effective supervision. To address the above problems, we propose the Coupling Sequence Model (COSMO) for TV recommendation. In COSMO, we design a session-aware co-attention mechanism that uses both the candidate item and session behaviors as the query to attend to the historical behaviors in a fine-grained manner. Furthermore, we propose to use the data of accounts with multiple devices (e.g., families with various TV sets), which means the behaviors of one account are generated on different devices. We regard the device information as weak supervision and propose a novel pair-wise attention loss for learning to distinguish the coupling behaviors. Extensive offline experiments and online A/B tests over a commercial TV service provider demonstrate the efficacy of COSMO compared to the existing models.

Reranking, as the final stage of multi-stage recommender systems, refines the initial lists to maximize the total utility. With the development of multimedia and user interface design, the recommendation page has evolved to a multi-list style. Separately employing traditional list-level reranking methods for different lists overlooks the inter-list interactions and the effect of different page formats, thus yielding suboptimal reranking performance. Moreover, simply applying a shared network for all the lists fails to capture the commonalities and distinctions in user behaviors on different lists. To this end, we propose to draw a bird's-eye view of page-level reranking and design a novel Page-level Attentional Reranking (PAR) model. We introduce a hierarchical dual-side attention module to extract personalized intra- and inter-list interactions. A spatial-scaled attention network is devised to integrate the spatial relationship into pairwise item influences, which explicitly models the page format. The multi-gated mixture-of-experts module is further applied to capture the commonalities and differences of user behaviors between different lists. Extensive experiments on a public dataset and a proprietary dataset show that PAR significantly outperforms existing baseline models.

Considering the balance between revenue and resource consumption for industrial recommender systems, intelligent recommendation computing has been emerging recently. Existing solutions deploy the same recommendation model to serve users indiscriminately, which is sub-optimal for total revenue maximization. We propose a multi-model service solution by deploying different-complexity models to serve different-valued users. An automated dynamic model generation framework AutoGen is elaborated to efficiently derive multiple parameter-sharing models with diverse complexities and adequate predictive capabilities. A mixed search space is designed and an importance-aware progressive training scheme is proposed to prevent interference between different architectures, which avoids the model retraining and improves the search efficiency, thereby efficiently deriving multiple models. Extensive experiments are conducted on two public datasets to demonstrate the effectiveness and efficiency of AutoGen.

Although reinforcement learning (RL) techniques are regarded as promising solutions for interactive recommender systems (IRS), such solutions still face three main challenges, namely, i) time inefficiency when handling large discrete action space in IRS, ii) inability to deal with the cold-start scenarios in IRS, iii) data inefficiency during training the RL-based methods. To tackle these challenges, we propose a generic tree-structured RL framework taking both policy-based and value-based approaches into consideration. We propose to construct a balanced tree over representations of the items, such that picking an item is formulated as seeking a suitable path from the root to a leaf node in the balanced tree, which dramatically reduces the time complexity of item recommendation. Further, for cold-start scenarios where prior information of the items is unavailable, we initialize a random balanced tree as the starting point and then refine the tree structure based on the learned item representations. Besides, we also incorporate a user modeling component to explicitly model the environment, which can be utilized in the training phase to improve data efficiency. Extensive experiments on two real-world datasets are conducted and demonstrate that our framework can achieve superior recommendation performance and provide time and data efficiency improvement over state-of-the-art methods in both warm-start and cold-start IRS scenarios.

Feature embedding learning and feature interaction modeling are two crucial components of deep models for Click-Through Rate (CTR) prediction in recommender systems. Most existing deep CTR models suffer from the following three problems. First, feature interactions are either manually designed or simply enumerated. However, not all the feature interactions are useful for the prediction task and useless feature interactions may introduce noisy signals thus causing overfitting. Second, all the feature interactions are modeled with an identical interaction function, whereas different interaction functions introduce different inductive biases to better capture various feature interaction patterns. Third, in most existing models, different features share the same embedding size. However, model size can be further optimized without sacrificing performance by differentiating embedding sizes for individual features, as the amount of information contained in each feature varies much. To address the three issues mentioned above, we proposeAutomatic Interaction Machine (AIM)with three core components, namely, Feature Interaction Search (FIS), Interaction Function Search (IFS) and Embedding Dimension Search (EDS), respectively. To tackle the first problem, FIS component automatically identifies different orders of essential feature interactions with useless ones pruned. Taking care of the second problem, IFS component selects appropriate interaction functions for each individual feature interaction in a learnable way. Moreover, to avoid learning conflict among different interaction functions, IFS proposes function-wise embeddings via performing multiple embeddings for each feature, where each feature embedding corresponds to one possible interaction function. However, utilizing multiple embeddings for each feature may make the model size affordably large if we keep the same embedding size as utilizing shared embedding (i.e., each feature shares the same embedding for different interaction functions). To solve this third problem, EDS automatically selects proper embedding size for each feature. Such a flexible embedding size adaptation is able to reduce the large amount of embedding parameters introduced by function-wise embeddings. Offline experiments on three large-scale datasets (two public benchmarks, one private dataset) validate that AIM can significantly improve various FM-based models. AIM has been deployed in the recommendation service of a mainstream app market, where a three-week online A/B test demonstrated the superiority of AIM, improving DeepFM model by 4.4% in terms of CTR.

Click-through rate (CTR) estimation plays a crucial role in modern online personalization services. It is essential to capture users’ drifting interests by modeling sequential user behaviors to build an accurate CTR estimation model. However, as the users accumulate a large amount of behavioral data on the online platforms, the current CTR models have to truncate user behavior sequences and utilize the most recent behaviors, which leads to a problem that sequential patterns such as periodicity or long-term dependency are not contained in the recent behaviors but in far back history. However, it is non-trivial to model the entire user sequence by directly using it for two reasons. Firstly, the very long input sequences will make online inference time and system load infeasible. Secondly, the very long sequences contain much noise, thus making it difficult for CTR models to capture useful patterns effectively. To tackle this issue, we consider it from the input data perspective instead of designing more sophisticated yet complex models. As the entire user behavior sequence contains much noise, it is unnecessary to input the entire sequence. Instead, we could just retrieve only a small part of it as the input to the CTR model. In this article, we propose the U ser B ehavior R etrieval (UBR) framework which aims at learning to retrieve the most informative user behaviors according to each CTR estimation request. Retrieving only a small set of behaviors could alleviate the two problems of utilizing very long sequences (i.e., inference efficiency and noisy input). The distinguishing property of UBR is that it supports arbitrary and learnable retrieval functions instead of utilizing a fixed pre-defined function, which is different from the current retrieval-based methods. Offline evaluations on three large-scale real-world datasets demonstrate the superiority and efficacy of the UBR framework. We further deploy UBR at the Huawei App Store, where it achieves 6.6% of eCPM gain in the online A/B test and now serves the main traffic in the Huawei App Store advertising scenario.

Modelling the user's multiple behaviors is an essential part of modern e-commerce, whose widely adopted application is to jointly optimize click-through rate (CTR) and conversion rate (CVR) predictions. Most of existing methods overlook the effect of two key characteristics of the user's behaviors: for each item list, (i) contextual dependence refers to that the user's behaviors on any item are not purely determinated by the item itself but also are influenced by the user's previous behaviors (e.g., clicks, purchases) on other items in the same sequence; (ii) multiple time scales means that users are likely to click frequently but purchase periodically. To this end, we develop a new multi-scale user behavior network named H ierarchical r E current R anking O n the E ntire S pace (HEROES) which incorporates the contextual information to estimate the user multiple behaviors in a multi-scale fashion. Concretely, we introduce a hierarchical framework, where the lower layer models the user's engagement behaviors while the upper layer estimates the user's satisfaction behaviors. The proposed architecture can automatically learn a suitable time scale for each layer to capture the dynamic user's behavioral patterns. Besides the architecture, we also introduce the Hawkes process to form a novel recurrent unit which can not only encode the items' features in the context but also formulate the excitation or discouragement from the user's previous behaviors. We further show that HEROES can be extended to build unbiased ranking systems through combinations with the survival analysis technique. Extensive experiments over three large-scale industrial datasets demonstrate the superiority of our model compared with the state-of-the-art methods. characteristics of the user's behaviors: for each item list, (i) contex- tual dependence refers to that the user's behaviors on any item are not purely determinated by the item itself but also are influenced by the user's previous behaviors (e.g., clicks, purchases) on other items in the same sequence; (ii) multiple time scales means that users are likely to click frequently but purchase periodically. To this end, we develop a new multi-scale user behavior network named Hierarchical rEcurrent Ranking On the Entire Space (HEROES) which incorporates the contextual information to estimate the user multiple behaviors in a multi-scale fashion. Concretely, we intro- duce a hierarchical framework, where the lower layer models the user's engagement behaviors while the upper layer estimates the user's satisfaction behaviors. The proposed architecture can auto- matically learn a suitable time scale for each layer to capture the dynamic user's behavioral patterns. Besides the architecture, we also introduce the Hawkes process to form a novel recurrent unit which can not only encode the items' features in the context but also formulate the excitation or discouragement from the user's previous behaviors. We further show that HEROES can be extended to build unbiased ranking systems through combinations with the survival analysis technique. Extensive experiments over three large- scale industrial datasets demonstrate the superiority of our model compared with the state-of-the-art methods.

In recent years, machine learning methods have been widely used in modern electronic health record (EHR) systems, and have shown more accurate prediction performance on disease risk assessment tasks than traditional methods. However, most of the existing machine learning methods make the assessment solely based on features of the target case but ignore the cross-sample feature interactions between the target case and other similar cases, which is inconsistent with the general practice of evidence-based medicine of making diagnoses based on existing clinical experience. Moreover, current methods that focus on mining cross-sample information rely on deep neural networks to extract cross-sample feature interactions, which would suffer from the problems of data insufficiency, data heterogeneity and lack of interpretability in disease risk assessment tasks. In this work, we propose a novel retrieval-based gradient boosting decision trees (RB-GBDT) model with a cross-sample extractor to mine cross-sample information while exploiting the superiority of GBDT of robustness, generalization and interpretability. Experiments on real-world clinical datasets show the superiority and efficacy of RB-GBDT on disease risk assessment tasks. The developed software has been deployed in hospital as an auxiliary diagnosis tool for risk assessment of venous thromboembolism.

As one of the fundamental trends for future development of recommender systems, Fashion Clothes Matching Recommendation for click-through rate (CTR) prediction has become an increasingly essential task. Unlike traditional single-item recommendation, a combo item, composed of a top item (e.g. a shirt) and a bottom item (e.g. a skirt), is recommended. In such a task, the matching effect between these two single items plays a crucial role, and greatly influences the users' preferences; however, it is usually neglected by previous approaches in CTR prediction. In this work, we tackle this problem by designing a novel algorithm called Combo-Fashion, which extracts the matching effect by introducing the matching history of the combo item with two cascaded modules: (i) Matching Search Module (MSM) seeks the popular combo items and undesirable ones as a positive set and a negative set, respectively; (ii) Matching Prediction Module (MPM) models the precise relationship between the candidate combo item and the positive/negative set by an attention-based deep model. Besides, the CPM Fashion Attribute, considered from characteristic, pattern and material, is applied to capture the matching effect further. As part of this work, we release two large-scale datasets consisting of 3.56 million and 6.01 million user behaviors with rich context and fashion information in millions of combo items. The experimental results over these two real-world datasets have demonstrated the superiority of our proposed model with significant improvements. Furthermore, we have deployed Combo-Fashion onto the platform of Taobao to recommend the combo items to the users, where an 8-day online A/B test proved the effectiveness of Combo-Fashion with an improvement of pCTR by 1.02% and uCTR by 0.70%.

User-tag profile modeling has become one of the novel and significant trends for the future development of industrial recommendation systems, which can be divided into two fundamental tasks: User Preferred Tag (UPT) and Tag Preferred User (TPU) in practical scenarios. In most existing deep learning models for user-tag profiling, the network inputs all the combined tags of the item with the user features when training but inputs only one tag with the user feature to evaluate the user's preference on a single tag when testing. This leads to data discrepancy between the training and testing samples. To address such an issue, we attempt a novel Random Masking Model (RMM) to remain only one tag at the training time by masking. However, it causes two other serious downsides. First, not all tags attached to the same item are equally predictive. Irrelevant tags may introduce noisy signals and thus cause performance degradation. Second, it neglects the impact of combined tags aggregated together, which may be an essential factor leading to user clicks. Therefore, we further propose a framework called Contrast Weighted Tag Masking (CWTM) in this work, which tackles these two issues with two modules: (i) Weighted Masking Module (WMM) introduces the importance network to compute a score for each tag attached to the item and then samples from these tags weightedly according to the score; (ii) Contrast Module (CM) makes use of a contrastive learning architecture to inherit and distill some understanding about the effect of aggregated tags. Offline experiments on four datasets (three public datasets and one proprietary industrial dataset) demonstrate the superiority and effectiveness of CWTM over the state-of-the-art baselines. Moreover, CWTM has been deployed on the training platform of Alibaba advertising systems and achieved substantial improvements of ROI and CVR by 16.8% and 9.6%, respectively.

Building a multi-stage cascade ranking system is a commonly used solution to balance the efficiency and effectiveness in modern information retrieval (IR) applications, such as recommendation and web search. Despite the popularity in practice, the literature specific on multi-stage cascade ranking systems is relatively scarce. The common practice is to train rankers of each stage independently using the same user feedback data (a.k.a., impression data), disregarding the data flow and the possible interactions between stages. This straightforward solution could lead to a sub-optimal system because of the sample selection bias (SSB) issue, which is especially damaging for cascade rankers due to the negative effect accumulated in the multiple stages. Worse still, the interactions between the rankers of each stage are not fully exploited. This paper provides an elaborate analysis of this commonly used solution to reveal its limitations. By studying the essence of cascade ranking, we propose a joint training framework named RankFlow to alleviate the SSB issue and exploit the interactions between the cascade rankers, which is the first systematic solution for this topic. We propose a paradigm of training cascade rankers that emphasizes the importance of fitting rankers on stage-specific data distributions instead of the unified user feedback distribution. We design the RankFlow framework based on this paradigm: The training data of each stage is generated by its preceding stages while the guidance signals not only come from the logs but its successors. Extensive experiments are conducted on various IR scenarios, including recommendation, web search and advertisement. The results verify the efficacy and superiority of RankFlow.

As the final stage of the multi-stage recommender system (MRS), reranking directly affects users' experience and satisfaction, thus playing a critical role in MRS. Despite the improvement achieved in the existing work, three issues are yet to be solved. First, users' historical behaviors contain rich preference information, such as users' long and short-term interests, but are not fully exploited in reranking. Previous work typically treats items in history equally important, neglecting the dynamic interaction between the history and candidate items. Second, existing reranking models focus on learning interactions at the item level while ignoring the fine-grained feature-level interactions. Lastly, estimating the reranking score on the ordered initial list before reranking may lead to the early scoring problem, thereby yielding suboptimal reranking performance. To address the above issues, we propose a framework named Multi-level Interaction Reranking (MIR). MIR combines low-level cross-item interaction and high-level set-to-list interaction, where we view the candidate items to be reranked as a set and the users' behavior history in chronological order as a list. We design a novel SLAttention structure for modeling the set-to-list interactions with personalized long-short term interests. Moreover, feature-level interactions are incorporated to capture the fine-grained influence among items. We design MIR in such a way that any permutation of the input items would not change the output ranking, and we theoretically prove it. Extensive experiments on three public and proprietary datasets show that MIR significantly outperforms the state-of-the-art models using various ranking and utility metrics.

Knowledge tracing, which estimates students' knowledge states by predicting the probability that they correctly answer questions, is an essential task for online learning platforms. It has gained much attention in the decades due to its importance to downstream tasks like learning material arrangement, etc. The previous deep learning-based methods trace students' knowledge states with the explicitly intra-student information, i.e., they only consider the historical information of individuals to make predictions. However, they neglect the inter-student information, which contains the response correctness of other students who have similar question-answering experiences, may offer some valuable clues. Based on this consideration, we propose a method called Collaborative Knowledge Tracing (CoKT) in this paper, which sufficiently exploits the inter-student information in knowledge tracing. It retrieves the sequences of peer students who have similar question-answering experiences to obtain the inter-student information, and integrates the inter-student information with the intra-student information to trace students' knowledge states and predict their correctness in answering questions. We validate the effectiveness of our method on four real-world datasets and compare it with 11 baselines. The experimental results reveal that CoKT achieves the best performance.

The personalized recommendation is an essential part of modern e-commerce, where user’s demands are not only conditioned by their profile but also by their recent browsing behaviors as well as periodical purchases made some time ago. In this paper, we propose a novel framework named Search-based Time-Aware Recommendation (STARec), which captures the evolving demands of users over time through a unified search-based time-aware model. More concretely, we first design a search-based module to retrieve a user’s relevant historical behaviors, which are then mixed up with her recent records to be fed into a time-aware sequential network for capturing her time-sensitive demands. Besides retrieving relevant information from her personal history, we also propose to search and retrieve similar user’s records as an additional reference. All these sequential records are further fused to make the final recommendation. Beyond this framework, we also develop a novel label trick that uses the previous labels (i.e., user’s feedbacks) as the input to better capture the user’s browsing pattern. We conduct extensive experiments on three real-world commercial datasets on click-through-rate prediction tasks against state-of-the-art methods. Experimental results demonstrate the superiority and efficiency of our proposed framework and techniques. Furthermore, results of online experiments on a daily item recommendation platform of Company X show that STARec gains average performance improvement of around 6% and 1.5% in its two main item recommendation scenarios on CTR metric respectively.

With the prevalence of live broadcast business nowadays, a new type of recommendation service, called live broadcast recommendation, is widely used in many mobile e-commerce Apps. Different from classical item recommendation, live broadcast recommendation is to automatically recommend user anchors instead of items considering the interactions among triple-objects (i.e., users, anchors, items) rather than binary interactions between users and items. Existing methods based on binary objects, ranging from early matrix factorization to recently emerged deep learning, obtain objects’ embeddings by mapping from pre-existing features. Directly applying these techniques would lead to limited performance, as they are failing to encode collaborative signals among triple-objects. In this paper, we propose a novel TWo-side Interactive NetworkS (TWINS) for live broadcast recommendation. In order to fully use both static and dynamic information on user and anchor sides, we combine a product-based neural network with a recurrent neural network to learn the embedding of each object. In addition, instead of directly measuring the similarity, TWINS effectively injects the collaborative effects into the embedding process in an explicit manner by modeling interactive patterns between the user’s browsing history and the anchor’s broadcast history in both item and anchor aspects. Furthermore, we design a novel co-retrieval technique to select key items among massive historic records efficiently. Offline experiments on real large-scale data show the superior performance of the proposed TWINS, compared to representative methods; and further results of online experiments on Diantao App show that TWINS gains average performance improvement of around 8% on ACTR metric, 3% on UCTR metric, 3.5% on UCVR metric.

Predicting urban traffic is of great importance to intelligent transportation systems and public safety, yet is very challenging in three aspects: 1) complex spatio-temporal correlations of urban traffic, including spatial correlations between locations along with temporal correlations among timestamps; 2) spatial diversity of such spatio-temporal correlations, which varies from location to location and depends on the surrounding geographical information, e.g., points of interests and road networks; and 3) temporal diversity of such spatio-temporal correlations, which is highly influenced by dynamic traffic states. To tackle these challenges, we proposed a deep meta learning based model, entitled ST-MetaNet$^+$+, tocollectivelypredict traffic in all locations at the same time. ST-MetaNet$^+$+employs a sequence-to-sequence architecture, consisting of an encoder to learn historical information and a decoder to make predictions step by step. Specifically, the encoder and decoder have the same network structure, consisting of meta graph attention networks and meta recurrent neural networks, to capture diverse spatial and temporal correlations, respectively. Furthermore, the weights (parameters) of meta graph attention networks and meta recurrent neural networks are generated from the embeddings of geo-graph attributes and the traffic context learned from dynamic traffic states. Extensive experiments were conducted based on three real-world datasets to illustrate the effectiveness of ST-MetaNet$^+$+beyond several state-of-the-art methods.

Learning to rank from logged user feedback, such as clicks or purchases, is a central component of many real-world information systems. Different from human-annotated relevance labels, the user feedback is always noisy and biased. Many existing learning to rank methods infer the underlying relevance of query–item pairs based on different assumptions of examination, and still optimize a relevance based objective. Such methods rely heavily on the correct estimation of examination, which is often difficult to achieve in practice. In this work, we propose a general framework U-rank+ for learning to rank with logged user feedback from the perspective of graph matching. We systematically analyze the biases in user feedback, including examination bias and selection bias. Then, we take both biases into consideration for unbiased utility estimation that directly based on user feedback, instead of relevance. In order to maximize the estimated utility in an efficient manner, we design two different solvers based on Sinkhorn and LambdaLoss for U-rank+ . The former is based on a standard graph matching algorithm, and the latter is inspired by the traditional method of learning to rank. Both of the algorithms have good theoretical properties to optimize the unbiased utility objective while the latter is proved to be empirically more effective and efficient in practice. Our framework U-rank+ can deal with a general utility function and can be used in a widespread of applications including web search, recommendation, and online advertising. Semi-synthetic experiments on three benchmark learning to rank datasets demonstrate the effectiveness of U-rank+ . Furthermore, our proposed framework has been deployed on two different scenarios of a mainstream App store, where the online A/B testing shows that U-rank+ achieves an average improvement of 19.2% on click-through rate and 20.8% improvement on conversion rate in recommendation scenario, and 5.12% on platform revenue in online advertising scenario over the production baselines.

Heterogeneous information network (HIN) has been widely used to characterize entities of various types and their complex relations. Recent attempts either rely on explicit path reachability to leverage path-based semantic relatedness or graph neighborhood to learn heterogeneous network representations before predictions. These weakly coupled manners overlook the rich interactions among neighbor nodes, which introduces an early summarization issue. In this article, we propose GraphHINGE ( H eterogeneous IN teract and aggre G at E ), which captures and aggregates the interactive patterns between each pair of nodes through their structured neighborhoods. Specifically, we first introduce Neighborhood-based Interaction (NI) module to model the interactive patterns under the same metapaths, and then extend it to Cross Neighborhood-based Interaction (CNI) module to deal with different metapaths. Next, in order to address the complexity issue on large-scale networks, we formulate the interaction modules via a convolutional framework and learn the parameters efficiently with fast Fourier transform. Furthermore, we design a novel neighborhood-based selection (NS) mechanism, a sampling strategy, to filter high-order neighborhood information based on their low-order performance. The extensive experiments on six different types of heterogeneous graphs demonstrate the performance gains by comparing with state-of-the-arts in both click-through rate prediction and top-N recommendation tasks.

Diabetes prediction is an important data science application in the social healthcare domain. There exist two main challenges in the diabetes prediction task: data heterogeneity since demographic and metabolic data are of different types, data insufficiency since the number of diabetes cases in a single medical center is usually limited. To tackle the above challenges, we employ gradient boosting decision trees (GBDT) to handle data heterogeneity and introduce multi-task learning (MTL) to solve data insufficiency. To this end, Task-wise Split Gradient Boosting Trees (TSGB) is proposed for the multi-center diabetes prediction task. Specifically, we firstly introduce task gain to evaluate each task separately during tree construction, with a theoretical analysis of GBDT's learning objective. Secondly, we reveal a problem when directly applying GBDT in MTL, i.e., the negative task gain problem. Finally, we propose a novel split method for GBDT in MTL based on the task gain statistics, named task-wise split, as an alternative to standard feature-wise split to overcome the mentioned negative task gain problem. Extensive experiments on a large-scale real-world diabetes dataset and a commonly used benchmark dataset demonstrate TSGB achieves superior performance against several state-of-the-art methods. Detailed case studies further support our analysis of negative task gain problems and provide insightful findings. The proposed TSGB method has been deployed as an online diabetes risk assessment software for early diagnosis.

Prediction over tabular data is an essential task in many data science applications such as recommender systems, online advertising, medical treatment, etc. Tabular data is structured into rows and columns, with each row as a data sample and each column as a feature attribute. Both the columns and rows of the tabular data carry useful patterns that could improve the model prediction performance. However, most existing models focus on the cross-column patterns yet overlook the cross-rowpatterns as they deal with single samples independently. In this work, we propose a general learning framework named Retrieval & Interaction Machine (RIM) that fully exploits both cross-row and cross-column patterns among tabular data. Specifically, RIM first leverages search engine techniques to efficiently retrieve useful rows of the table to assist the label prediction of the target row, then uses feature interaction networks to capture the cross-column patterns among the target row and the retrieved rows so as to make the final label prediction. We conduct extensive experiments on 11 datasets of three important tasks, i.e., CTR prediction (classification), top-n recommendation (ranking) and rating prediction (regression). Experimental results show that RIM achieves significant improvements over the state-of-the-art and various baselines, demonstrating the superiority and efficacy of RIM.

To better exploit search logs and model users' behavior patterns, numerous click models are proposed to extract users' implicit interaction feedback. Most traditional click models are based on the probabilistic graphical model (PGM) framework, which requires manually designed dependencies and may oversimplify user behaviors. Recently, methods based on neural networks are proposed to improve the prediction accuracy of user behaviors by enhancing the expressive ability and allowing flexible dependencies. However, they still suffer from the data sparsity and cold-start problems. In this paper, we propose a novel graph-enhanced click model (GraphCM) for web search. Firstly, we regard each query or document as a vertex, and propose novel homogeneous graph construction methods for queries and documents respectively, to fully exploit both intra-session and inter-session information for the sparsity and cold-start problems. Secondly, following the examination hypothesis, we separately model the attractiveness estimator and examination predictor to output the attractiveness scores and examination probabilities, where graph neural networks and neighbor interaction techniques are applied to extract the auxiliary information encoded in the pre-constructed homogeneous graphs. Finally, we apply combination functions to integrate examination probabilities and attractiveness scores into click predictions. Extensive experiments conducted on three real-world session datasets show that GraphCM not only outperforms the state-of-art models, but also achieves superior performance in addressing the data sparsity and cold-start problems.

Knowledge tracing, which dynamically estimates students' learning states by predicting their performance on answering questions, is an essential task in online education. One typical solution for knowledge tracing is based on Recurrent Neural Networks (RNNs), which represent students' knowledge states with the hidden states of RNNs. Such type of methods normally assumes that students have the same cognition level and knowledge acquisition sensitivity on the same question. Thus, they (i) predict students' responses by referring to their knowledge states and question representations, and (ii) update the knowledge states according to the question representations and students' responses. No explicit cognition level or knowledge acquisition sensitivity is considered in the above two processes. However, in real-world scenarios, students have different understandings on a question and have various knowledge acquisition after they finish the same question. In this paper, we propose a novel model called Individual Estimation Knowledge Tracing (IEKT), which estimates the students' cognition on the question before response prediction and assesses their knowledge acquisition sensitivity on the questions before updating the knowledge state. In the experiments, we compare IEKT with 11 knowledge tracing baselines on four benchmark datasets, and the results show IEKT achieves the state-of-the-art performance.

Modern information retrieval systems, including web search, ads placement, and recommender systems, typically rely on learning from user feedback. Click models, which study how users interact with a ranked list of items, provide a useful understanding of user feedback for learning ranking models. Constructing ”right” dependencies is the key of any successful click model. However, probabilistic graphical models (PGMs) have to rely on manually assigned dependencies, and oversimplify user behaviors. Existing neural network based methods promote PGMs by enhancing the expressive ability and allowing flexible dependencies, but still suffer from exposure bias and inferior estimation. In this paper, we propose a novel framework, Adversarial Imitation Click Model (AICM), based on imitation learning. Firstly, we explicitly learn the reward function that recovers users’ intrinsic utility and underlying intentions. Secondly, we model user interactions with a ranked list as a dynamic system instead of one-step click prediction, alleviating the exposure bias problem. Finally, we minimize the JS divergence through adversarial training and learn a stable distribution of click sequences, which makes AICM generalize well across different distributions of ranked lists. A theoretical analysis has indicated that AICM reduces the exposure bias from O(T2) to O(T). Our studies on a public web search dataset show that AICM not only outperforms state-of-the-art models in traditional click metrics but also achieves superior performance in addressing the exposure bias and recovering the underlying patterns of click sequences.

Spatio-temporal graphs are important structures to describe urban sensory data, e.g., traffic speed and air quality. Predicting over spatio-temporal graphs enables many essential applications in intelligent cities, such as traffic management and environment analysis. Recently, many deep learning models have been proposed for spatio-temporal graph prediction and achieved significant results. However, designing neural networks requires rich domain knowledge and expert efforts. To this end, we study automated neural architecture search for spatio-temporal graphs with the application to urban traffic prediction, which meets two challenges: 1) how to define search space for capturing complex spatio-temporal correlations; and 2) how to learn network weight parameters related to the corresponding attributed graph of a spatio-temporal graph.

Learning to rank with implicit feedback is one of the most important tasks in many real-world information systems where the objective is some specific utility, e.g., clicks and revenue. However, we point out that existing methods based on probabilistic ranking principle do not necessarily achieve the highest utility. To this end, we propose a novel ranking framework called U-rank that directly optimizes the expected utility of the ranking list. With a position-aware deep click-through rate prediction model, we address the attention bias considering both query-level and item-level features. Due to the item-specific attention bias modeling, the optimization for expected utility corresponds to a maximum weight matching on the item-position bipartite graph. We base the optimization of this objective in an efficient Lambdaloss framework, which is supported by both theoretical and empirical analysis. We conduct extensive experiments for both web search and recommender systems over three benchmark datasets and two proprietary datasets, where the performance gain of U-rank over state-of-the-arts is demonstrated. Moreover, our proposed U-rank has been deployed on a large-scale commercial recommender and a large improvement over the production baseline has been observed in an online A/B testing.

The heavy traffic congestion problem has always been a concern for modern cities. To alleviate traffic congestion, researchers use reinforcement learning (RL) to develop better traffic signal control (TSC) algorithms in recent years. However, most RL models are trained and tested in the same traffic flow environment, which results in a serious overfitting problem. Since the traffic flow environment in the real world keeps varying, these models can hardly be applied due to the lack of generalization ability. Besides, the limited number of accessible traffic flow data brings extra difficulty in testing the generalization ability of the models. In this paper, we design a novel traffic flow generator based on Wasserstein generative adversarial network to generate sufficient diverse and quality traffic flows and use them to build proper training and testing environments. Then we propose a meta-RL TSC framework GeneraLight to improve the generalization ability of TSC models. GeneraLight boosts the generalization performance by combining the idea of flow clustering and model-agnostic meta-learning. We conduct extensive experiments on multiple real-world datasets to show the superior performance of GeneraLight on generalizing to different traffic flows.

There is an influx of heterogeneous information network (HIN) based recommender systems in recent years since HIN is capable of characterizing complex graphs and contains rich semantics. Although the existing approaches have achieved performance improvement, while practical, they still face the following problems. On one hand, most existing HIN-based methods rely on explicit path reachability to leverage path-based semantic relatedness between users and items, e.g., metapath-based similarities. These methods are hard to use and integrate since path connections are sparse or noisy, and are often of different lengths. On the other hand, other graph-based methods aim to learn effective heterogeneous network representations by compressing node together with its neighborhood information into single embedding before prediction. This weakly coupled manner in modeling overlooks the rich interactions among nodes, which introduces an early summarization issue. In this paper, we propose an end-to-end Neighborhood-based Interaction Model for Recommendation (NIRec) to address above problems. Specifically, we first analyze the significance of learning interactions in HINs and then propose a novel formulation to capture the interactive patterns between each pair of nodes through their metapath-guided neighborhoods. Then, to explore complex interactions between metapaths and deal with the learning complexity on large-scale networks, we formulate interaction in a convolutional way and learn efficiently with fast Fourier transform. The extensive experiments on four different types of heterogeneous graphs demonstrate the performance gains of NIRec comparing with state-of-the-arts. To the best of our knowledge, this is the first work providing an efficient neighborhood-based interaction model in the HIN-based recommendations.

Learning feature interactions is crucial for click-through rate (CTR) prediction in recommender systems. In most existing deep learning models, feature interactions are either manually designed or simply enumerated. However, enumerating all feature interactions brings large memory and computation cost. Even worse, useless interactions may introduce noise and complicate the training process. In this work, we propose a two-stage algorithm called Automatic Feature Interaction Selection (AutoFIS). AutoFIS can automatically identify important feature interactions for factorization models with computational cost just equivalent to training the target model to convergence. In the search stage, instead of searching over a discrete set of candidate feature interactions, we relax the choices to be continuous by introducing the architecture parameters. By implementing a regularized optimizer over the architecture parameters, the model can automatically identify and remove the redundant feature interactions during the training process of the model. In the re-train stage, we keep the architecture parameters serving as an attention unit to further boost the performance. Offline experiments on three large-scale datasets (two public benchmarks, one private) demonstrate that AutoFIS can significantly improve various FM based models. AutoFIS has been deployed onto the training platform of Huawei App Store recommendation service, where a 10-day online A/B test demonstrated that AutoFIS improved the DeepFM model by 20.3% and 20.1% in terms of CTR and CVR respectively.

Position bias is a critical problem in information retrieval when dealing with implicit yet biased user feedback data. Unbiased ranking methods typically rely on causality models and debias the user feedback through inverse propensity weighting. While practical, these methods still suffer from two major problems. First, when infer a user click, the impact of the contextual information, such as documents that have been examined, is often ignored. Second, only the position bias is considered but other issues resulted from user browsing behaviors are overlooked. In this paper, we propose an end-to-end Deep Recurrent Survival Ranking (DRSR), a unified framework to jointly model user's various behaviors, to (i) consider the rich contextual information in the ranking list; and (ii) address the hidden issues underlying user behaviors, i.e., to mine observe pattern in queries without any click (non-click queries), and to model tracking logs which cannot truly reflect the user browsing intents (untrusted observation). Specifically, we adopt a recurrent neural network to model the contextual information and estimates the conditional likelihood of user feedback at each position. We then incorporate survival analysis techniques with the probability chain rule to mathematically recover the unbiased joint probability of one user's various behaviors. DRSR can be easily incorporated with both point-wise and pair-wise learning objectives. The extensive experiments over two large-scale industrial datasets demonstrate the significant performance gains of our model comparing with the state-of-the-arts.

Click-through rate (CTR) prediction plays a key role in modern online personalization services. In practice, it is necessary to capture user's drifting interests by modeling sequential user behaviors to build an accurate CTR prediction model. However, as the users accumulate more and more behavioral data on the platforms, it becomes non-trivial for the sequential models to make use of the whole behavior history of each user. First, directly feeding the long behavior sequence will make online inference time and system load infeasible. Second, there is much noise in such long histories to fail the sequential model learning. The current industrial solutions mainly truncate the sequences and just feed recent behaviors to the prediction model, which leads to a problem that sequential patterns such as periodicity or long-term dependency are not embedded in the recent several behaviors but in far back history. To tackle these issues, in this paper we consider it from the data perspective instead of just designing more sophisticated yet complicated models and propose User Behavior Retrieval for CTR prediction (UBR4CTR) framework. In UBR4CTR, the most relevant and appropriate user behaviors will be firstly retrieved from the entire user history sequence using a learnable search method. These retrieved behaviors are then fed into a deep model to make the final prediction instead of simply using the most recent ones. It is highly feasible to deploy UBR4CTR into industrial model pipeline with low cost. Experiments on three real-world large-scale datasets demonstrate the superiority and efficacy of our proposed framework and models.

In this paper, we present the design of QuAChIE, a Question Answering based Chinese Information Extraction system. QuAChIE mainly depends on a well-trained question answering model to extract high-quality triples. The group of head entity and relation are regarded as a question given the input text as the context. For the training and evaluation of each model in the system, we build a large-scale information extraction dataset using Wikidata and Wikipedia pages by distant supervision. The advanced models implemented on top of the pre-trained language model and the enormous distant supervision data enable QuAChIE to extract relation triples from documents with cross-sentence correlations. The experimental results on the test set and the case study based on the interactive demonstration show its satisfactory Information Extraction quality on Chinese document-level texts.

Spaced repetition technique aims at improving long-term memory retention for human students by exploiting repeated, spaced reviews of learning contents. The study of spaced repetition focuses on designing an optimal policy to schedule the learning contents. To the best of our knowledge, none of the existing methods based on reinforcement learning take into account the varying time intervals between two adjacent learning events of the student, which, however, are essential to determine real-world schedule. In this paper, we aim to learn a scheduling policy that fully exploits the varying time interval information with high sample efficiency. We propose the Time-Aware scheduler with Dyna-Style planning (TADS) approach: a sample-efficient reinforcement learning framework for realistic spaced repetition. TADS learns a Time-LSTM policy to select an optimal content according to the student's whole learning history and the time interval since the last learning event. Besides, Dyna-style planning is integrated into TADS to further improve the sample efficiency. We evaluate our approach on three environments built from synthetic data and real-world data based on well-recognized cognitive models. Empirical results demonstrate that TADS achieves superior performance against state-of-the-art algorithms.

Interactive recommender system (IRS) has drawn huge attention because of its flexible recommendation strategy and the consideration of optimal long-term user experiences. To deal with the dynamic user preference and optimize accumulative utilities, researchers have introduced reinforcement learning (RL) into IRS. However, RL methods share a common issue of sample efficiency, i.e., huge amount of interaction data is required to train an effective recommendation policy, which is caused by the sparse user responses and the large action space consisting of a large number of candidate items. Moreover, it is infeasible to collect much data with explorative policies in online environments, which will probably harm user experience. In this work, we investigate the potential of leveraging knowledge graph (KG) in dealing with these issues of RL methods for IRS, which provides rich side information for recommendation decision making. Instead of learning RL policies from scratch, we make use of the prior knowledge of the item correlation learned from KG to (i) guide the candidate selection for better candidate item retrieval, (ii) enrich the representation of items and user states, and (iii) propagate user preferences among the correlated items over KG to deal with the sparsity of user feedback. Comprehensive experiments have been conducted on two real-world datasets, which demonstrate the superiority of our approach with significant improvements against state-of-the-arts.

Sequential recommendation task aims to predict user preference over items in the future given user historical behaviors. The order of user behaviors implies that there are resourceful sequential patterns embedded in the behavior history which reveal the underlying dynamics of user interests. Various sequential recommendation methods are proposed to model the dynamic user behaviors. However, most of the models only consider the user's own behaviors and dynamics, while ignoring the collaborative relations among users and items, i.e., similar tastes of users or analogous properties of items. Without modeling collaborative relations, those methods suffer from the lack of recommendation diversity and thus may have worse performance. Worse still, most existing methods only consider the user-side sequence and ignore the temporal dynamics on the item side. To tackle the problems of the current sequential recommendation models, we propose Sequential Collaborative Recommender (SCoRe) which effectively mines high-order collaborative information using cross-neighbor relation modeling and, additionally utilizes both user-side and item-side historical sequences to better capture user and item dynamics. Experiments on three real-world yet large-scale datasets demonstrate the superiority of the proposed model over strong baselines.

Predicting urban flow is essential for city risk assessment and traffic management, which profoundly impacts people's lives and property. Recently, some deep learning models, focusing on capturing spatio-temporal (ST) correlations between urban regions, have been proposed to predict urban flows. However, these models overlook latent region functions that impact ST correlations greatly. Thus, it is necessary to have a framework to assist these deep models in tackling the region function issue. However, it is very challenging because of two problems: 1) how to make deep models predict flows taking into consideration latent region functions; 2) how to make the framework generalize to a variety of deep models. To tackle these challenges, we propose a novel framework that employs matrix factorization for spatio-temporal neural networks (MF-STN), capable of enhancing the state-of-the-art deep ST models. MF-STN consists of two components: 1) a ST feature learner, which obtains features of ST correlations from all regions by the corresponding sub-networks in the existing deep models; and 2) a region-specific predictor, which leverages the learned ST features to make region-specific predictions. In particular, matrix factorization is employed on the neural networks, namely, decomposing the region-specific parameters of the predictor into learnable matrices, i.e., region embedding matrices and parameter embedding matrices, to model latent region functions and correlations among regions. Extensive experiments were conducted on two real-world datasets, illustrating that MF-STN can significantly improve the performance of some representative ST models while preserving model complexity.

Improving the efficiency of dispatching orders to vehicles is a research hotspot in online ride-hailing systems. Most of the existing solutions for order-dispatching are centralized controlling, which require to consider all possible matches between available orders and vehicles. For large-scale ride-sharing platforms, there are thousands of vehicles and orders to be matched at every second which is of very high computational cost. In this paper, we propose a decentralized execution order-dispatching method based on multi-agent reinforcement learning to address the large-scale order-dispatching problem. Different from the previous cooperative multi-agent reinforcement learning algorithms, in our method, all agents work independently with the guidance from an evaluation of the joint policy since there is no need for communication or explicit cooperation between agents. Furthermore, we use KL-divergence optimization at each time step to speed up the learning process and to balance the vehicles (supply) and orders (demand). Experiments on both the explanatory environment and real-world simulator show that the proposed method outperforms the baselines in terms of accumulated driver income (ADI) and Order Response Rate (ORR) in various traffic environments. Besides, with the support of the online platform of Didi Chuxing, we designed a hybrid system to deploy our model.

Trajectory data has been widely used in many urban applications. Sharing trajectory data with effective supervision is a vital task, as it contains private information of moving objects. However, malicious data users can modify trajectories in various ways to avoid data distribution tracking by the hashing-based data signatures, e.g., MD5. Moreover, the existing trajectory data protection scheme can only protect trajectories from either spatial or temporal modifications. Finally, so far there is no authoritative third party for trajectory data sharing process, as trajectory data is too sensitive. To this end, we propose a novel trajectory copyright protection scheme, which can protect trajectory data from comprehensive types of data modifications/attacks. Three main techniques are employed to effectively guarantee the robustness and comprehensiveness of the proposed data sharing scheme: 1) the identity information is embedded distributively across a set of sub-trajectories partitioned based on the spatio-temporal regions; 2) the centroid distance of the sub-trajectories is served as a stable trajectory attribute to embed the information; and 3) the blockchain technique is used as a trusted third party to log all data transaction history for data distribution tracking in a decentralized manner. Extensive experiments were conducted based on two real-world trajectory datasets to demonstrate the effectiveness of our proposed scheme.

Predicting urban traffic is of great importance to intelligent transportation systems and public safety, yet is very challenging because of two aspects: 1) complex spatio-temporal correlations of urban traffic, including spatial correlations between locations along with temporal correlations among timestamps; 2) diversity of such spatio-temporal correlations, which vary from location to location and depend on the surrounding geographical information, e.g., points of interests and road networks. To tackle these challenges, we proposed a deep-meta-learning based model, entitled ST-MetaNet, to collectively predict traffic in all location at once. ST-MetaNet employs a sequence-to-sequence architecture, consisting of an encoder to learn historical information and a decoder to make predictions step by step. In specific, the encoder and decoder have the same network structure, consisting of a recurrent neural network to encode the traffic, a meta graph attention network to capture diverse spatial correlations, and a meta recurrent neural network to consider diverse temporal correlations. Extensive experiments were conducted based on two real-world datasets to illustrate the effectiveness of ST-MetaNet beyond several state-of-the-art methods.

The emergence of real-time auction in online advertising has drawn huge attention of modeling the market competition, i.e., bid landscape forecasting. The problem is formulated as to forecast the probability distribution of market price for each ad auction. With the consideration of the censorship issue which is caused by the second-price auction mechanism, many researchers have devoted their efforts on bid landscape forecasting by incorporating survival analysis from medical research field. However, most existing solutions mainly focus on either counting-based statistics of the segmented sample clusters, or learning a parameterized model based on some heuristic assumptions of distribution forms. Moreover, they neither consider the sequential patterns of the feature over the price space. In order to capture more sophisticated yet flexible patterns at fine-grained level of the data, we propose a Deep Landscape Forecasting (DLF) model which combines deep learning for probability distribution forecasting and survival analysis for censorship handling. Specifically, we utilize a recurrent neural network to flexibly model the conditional winning probability w.r.t. each bid price. Then we conduct the bid landscape forecasting through probability chain rule with strict mathematical derivations. And, in an end-to-end manner, we optimize the model by minimizing two negative likelihood losses with comprehensive motivations. Without any specific assumption for the distribution form of bid landscape, our model shows great advantages over previous works on fitting various sophisticated market price distributions. In the experiments over two large-scale real-world datasets, our model significantly outperforms the state-of-the-art solutions under various metrics.

User response prediction, which models the user preference w.r.t. the presented items, plays a key role in online services. With two-decade rapid development, nowadays the cumulated user behavior sequences on mature Internet service platforms have become extremely long since the user's first registration. Each user not only has intrinsic tastes, but also keeps changing her personal interests during lifetime. Hence, it is challenging to handle such lifelong sequential modeling for each individual user. Existing methodologies for sequential modeling are only capable of dealing with relatively recent user behaviors, which leaves huge space for modeling long-term especially lifelong sequential patterns to facilitate user modeling. Moreover, one user's behavior may be accounted for various previous behaviors within her whole online activity history, i.e., long-term dependency with multi-scale sequential patterns. In order to tackle these challenges, in this paper, we propose a Hierarchical Periodic Memory Network for lifelong sequential modeling with personalized memorization of sequential patterns for each user. The model also adopts a hierarchical and periodical updating mechanism to capture multi-scale sequential patterns of user interests while supporting the evolving user behavior logs. The experimental results over three large-scale real-world datasets have demonstrated the advantages of our proposed model with significant improvement in user response prediction performance against the state-of-the-arts.

Knowledge base is one of the main forms to represent information in a structured way. A knowledge base typically consists of Resource Description Frameworks (RDF) triples which describe the entities and their relations. Generating natural language description of the knowledge base is an important task in NLP, which has been formulated as a conditional language generation task and tackled using the sequence-to-sequence framework. Current works mostly train the language models by maximum likelihood estimation, which tends to generate lousy sentences. In this paper, we argue that such a problem of maximum likelihood estimation is intrinsic, which is generally irrevocable via changing network structures. Accordingly, we propose a novel Triple-to-Text (T2T) framework, which approximately optimizes the inverse Kullback-Leibler (KL) divergence between the distributions of the real and generated sentences. Due to the nature that inverse KL imposes large penalty on fake-looking samples, the proposed method can significantly reduce the probability of generating low-quality sentences. Our experiments on three real-world datasets demonstrate that T2T can generate higher-quality sentences and outperform baseline models in several evaluation metrics.

In graphs with rich texts, incorporating textual information with structural information would benefit constructing expressive graph embeddings. Among various graph embedding models, random walk (RW)-based is one of the most popular and successful groups. However, it is challenged by two issues when applied on graphs with rich texts: (i) sampling efficiency: deriving from the training objective of RW-based models (e.g., DeepWalk and node2vec), we show that RW-based models are likely to generate large amounts of redundant training samples due to three main drawbacks. (ii) text utilization: these models have difficulty in dealing with zero-shot scenarios where graph embedding models have to infer graph structures directly from texts. To solve these problems, we propose a novel framework, namely Text-driven Graph Embedding with Pairs Sampling (TGE-PS). TGE-PS uses Pairs Sampling (PS) to improve the sampling strategy of RW, being able to reduce ~ 99% training samples while preserving competitive performance. TGE-PS uses Text-driven Graph Embedding (TGE), an inductive graph embedding approach, to generate node embeddings from texts. Since each node contains rich texts, TGE is able to generate high-quality embeddings and provide reasonable predictions on existence of links to unseen nodes. We evaluate TGE-PS on several real-world datasets, and experiment results demonstrate that TGE-PS produces state-of-the-art results on both traditional and zero-shot link prediction tasks.

Traffic signal control is an emerging application scenario for reinforcement learning. Besides being as an important problem that affects people's daily life in commuting, traffic signal control poses its unique challenges for reinforcement learning in terms of adapting to dynamic traffic environment and coordinating thousands of agents including vehicles and pedestrians. A key factor in the success of modern reinforcement learning relies on a good simulator to generate a large number of data samples for learning. The most commonly used open-source traffic simulator SUMO is, however, not scalable to large road network and large traffic flow, which hinders the study of reinforcement learning on traffic scenarios. This motivates us to create a new traffic simulator CityFlow with fundamentally optimized data structures and efficient algorithms. CityFlow can support flexible definitions for road network and traffic flow based on synthetic and real-world data. It also provides user-friendly interface for reinforcement learning. Most importantly, CityFlow is more than twenty times faster than SUMO and is capable of supporting city-wide traffic simulation with an interactive render for monitoring. Besides traffic signal control, CityFlow could serve as the base for other transportation studies and can create new possibilities to test machine learning methods in the intelligent transportation domain.

User response prediction is a crucial component for personalized information retrieval and filtering scenarios, such as recommender system and web search. The data in user response prediction is mostly in a multi-field categorical format and transformed into sparse representations via one-hot encoding. Due to the sparsity problems in representation and optimization, most research focuses on feature engineering and shallow modeling. Recently, deep neural networks have attracted research attention on such a problem for their high capacity and end-to-end training scheme. In this article, we study user response prediction in the scenario of click prediction. We first analyze a coupled gradient issue in latent vector-based models and propose kernel product to learn field-aware feature interactions. Then, we discuss an insensitive gradient issue in DNN-based models and propose Product-based Neural Network, which adopts a feature extractor to explore feature interactions. Generalizing the kernel product to a net-in-net architecture, we further propose Product-network in Network (PIN), which can generalize previous models. Extensive experiments on four industrial datasets and one contest dataset demonstrate that our models consistently outperform eight baselines on both area under curve and log loss. Besides, PIN makes great click-through rate improvement (relatively 34.67%) in online A/B test.

In online advertising, the Internet users may be exposed to a sequence of different ad campaigns, i.e., display ads, search, or referrals from multiple channels, before led up to any final sales conversion and transaction. For both campaigners and publishers, it is fundamentally critical to estimate the contribution from ad campaign touch-points during the customer journey (conversion funnel) and assign the right credit to the right ad exposure accordingly. However, the existing research on the multi-touch attribution problem lacks a principled way of utilizing the users' pre-conversion actions (i.e., clicks), and quite often fails to model the sequential patterns among the touch points from a user's behavior data. To make it worse, the current industry practice is merely employing a set of arbitrary rules as the attribution model, e.g., the popular last-touch model assigns 100% credit to the final touch-point regardless of actual attributions. In this paper, we propose a Dual-attention Recurrent Neural Network (DARNN) for the multi-touch attribution problem. It learns the attribution values through an attention mechanism directly from the conversion estimation objective. To achieve this, we utilize sequence-to-sequence prediction for user clicks, and combine both post-view and post-click attribution patterns together for the final conversion estimation. To quantitatively benchmark attribution models, we also propose a novel yet practical attribution evaluation scheme through the proxy of budget allocation (under the estimated attributions) over ad channels. The experimental results on two real datasets demonstrate the significant performance gains of our attribution model against the state of the art.

We introduce Texygen, a benchmarking platform to support research on open-domain text generation models. Texygen has not only implemented a majority of text generation models, but also covered a set of metrics that evaluate the diversity, the quality and the consistency of the generated texts. The Texygen platform could help standardize the research on text generation and improve the reproductivity and reliability of future research work in text generation.

Real-time bidding (RTB) based display advertising has become one of the key technological advances in computational advertising. RTB enables advertisers to buy individual ad impressions via an auction in real-time and facilitates the evaluation and the bidding of individual impressions across multiple advertisers. In RTB, the advertisers face three main challenges when optimizing their bidding strategies, namely (i) estimating the utility (e.g., conversions, clicks) of the ad impression, (ii) forecasting the market value (thus the cost) of the given ad impression, and (iii) deciding the optimal bid for the given auction based on the first two. Previous solutions assume the first two are solved before addressing the bid optimization problem. However, these challenges are strongly correlated and dealing with any individual problem independently may not be globally optimal. In this paper, we propose Bidding Machine, a comprehensive learning to bid framework, which consists of three optimizers dealing with each challenge above, and as a whole, jointly optimizes these three parts. We show that such a joint optimization would largely increase the campaign effectiveness and the profit. From the learning perspective, we show that the bidding machine can be updated smoothly with both offline periodical batch or online sequential training schemes. Our extensive offline empirical study and online A/B testing verify the high effectiveness of the proposed bidding machine.

Personalized recommendation has been proved effective as a content discovery tool for many online news publishers. As fresh news articles are frequently coming to the system while the old ones are fading away quickly, building a consistent and coherent feature representation over the ever-changing articles pool is fundamental to the performance of the recommendation. However, learning a good feature representation is challenging, especially for some small publishers that have normally fewer than 10,000 articles each year. In this paper, we consider to transfer knowledge from a larger text corpus. In our proposed solution, an effective article recommendation engine can be established with a small number of target publisher articles by transferring knowledge from a large corpus of text with a different distribution. Specifically, we leverage noise contrastive estimation techniques to learn the word conditional distribution given the context words, where the noise conditional distribution is pre-trained from the large corpus. Our solution has been deployed in a commercial recommendation service. The large-scale online A/B testing on two commercial publishers demonstrates up to 9.97% relative overall performance gain of our proposed model on the recommendation click-though rate metric over the non-transfer learning baselines.

Programmatic display advertising, which enables advertisers to make real-time decisions on individual ad display opportunities so as to achieve a precise audience marketing, has become a key technique for online advertising. However, the constrained budget setting still restricts unlimited ad impressions. As a result, a smart strategy for ad impression selection is necessary for the advertisers to maximize positive user responses such as clicks or conversions, under the constraints of both ad volume and campaign budget. In this paper, we borrow in the idea of top-N ranking and filtering techniques from information retrieval and propose an effective ad impression volume ranking method for each ad campaign, followed by a sequential selection strategy considering the remaining ad volume and budget, to smoothly deliver the volume filtering while maximizing campaign efficiency. The extensive experiments on two benchmarking datasets and a commercial ad platform demonstrate large performance superiority of our proposed solution over traditional methods, especially under tight budgets.

As aggregators, online news portals face great challenges in continuously selecting a pool of candidate articles to be shown to their users. Typically, those candidate articles are recommended manually by platform editors from a much larger pool of articles aggregated from multiple sources. Such a hand-pick process is labor intensive and time-consuming. In this paper, we study the editor article selection behavior and propose a learning by demonstration system to automatically select a subset of articles from the large pool. Our data analysis shows that (i) editors' selection criteria are non-explicit, which are less based only on the keywords or topics, but more depend on the quality and attractiveness of the writing from the candidate article, which is hard to capture based on traditional bag-of-words article representation. And (ii) editors' article selection behaviors are dynamic: articles with different data distribution come into the pool everyday and the editors' preference varies, which are driven by some underlying periodic or occasional patterns. To address such problems, we propose a meta-attention model across multiple deep neural nets to (i) automatically catch the editors' underlying selection criteria via the automatic representation learning of each article and its interaction with the meta data and (ii) adaptively capture the change of such criteria via a hybrid attention model. The attention model strategically incorporates multiple prediction models, which are trained in previous days. The system has been deployed in a commercial article feed platform. A 9-day A/B testing has demonstrated the consistent superiority of our proposed model over several strong baselines.

The majority of online display ads are served through real-time bidding (RTB) --- each ad display impression is auctioned off in real-time when it is just being generated from a user visit. To place an ad automatically and optimally, it is critical for advertisers to devise a learning algorithm to cleverly bid an ad impression in real-time. Most previous works consider the bid decision as a static optimization problem of either treating the value of each impression independently or setting a bid price to each segment of ad volume. However, the bidding for a given ad campaign would repeatedly happen during its life span before the budget runs out. As such, each bid is strategically correlated by the constrained budget and the overall effectiveness of the campaign (e.g., the rewards from generated clicks), which is only observed after the campaign has completed. Thus, it is of great interest to devise an optimal bidding strategy sequentially so that the campaign budget can be dynamically allocated across all the available impressions on the basis of both the immediate and future rewards. In this paper, we formulate the bid decision process as a reinforcement learning problem, where the state space is represented by the auction information and the campaign's real-time parameters, while an action is the bid price to set. By modeling the state transition via auction competition, we build a Markov Decision Process framework for learning the optimal bidding policy to optimize the advertising performance in the dynamic real-time bidding environment. Furthermore, the scalability problem from the large real-world auction volume and campaign budget is well handled by state value approximation using neural networks. The empirical study on two large-scale real-world datasets and the live A/B testing on a commercial platform have demonstrated the superior performance and high efficiency compared to state-of-the-art methods.

A large number of patients discuss treatments in online health communities (OHCs). One research question of interest to health researchers is whether treatments being discussed in OHCs are eventually used by community members in their real lives. In this paper, we rely on machine learning methods to automatically identify attributions of mentions of treatments from an online autism community. The context of our work is online autism communities, where parents exchange support for the care of their children with autism spectrum disorder. Our methods are able to distinguish discussions of treatments that are associated with patients, caregivers, and others, as well as identify whether a treatment is actually taken. We investigate treatments that are not just discussed but also used by patients according to two types of content analysis, cross-sectional and longitudinal. The treatments identified through our content analysis help create a catalogue of real-world treatments. This study results lay the foundation for future research to compare real-world drug usage with established clinical guidelines.

Authenticity is the key for online review sites. Due to the significant development of review sites, the reviews are now highly important to users, producers and other stakeholders. Driven by interest, some imposters begin to post fake reviews to promote or discredit target products. The fake reviews not only mislead the users but also damage the service provider's credit. Current works mostly aim at classifying whether a specific review is fake or not, using context-based or user-based approaches. However, the aggregated rating of the product is viewer's most concern. Therefore, we propose a novel task to restore the truthful rating and further tackle it by statistical and deep learning techniques. We also assemble and publish a movie-review dataset for this task.

Aligning heterogeneous online social networks is a highly beneficial task proposed in recent years. It targets at automatically aligning accounts from multiple networks by whether they are held by the same natural person. Aligning the networks can improve personalized services by cross-platform user modeling, and is the prerequisite for cross-network analysis. However, there is currently no public benchmark dataset available due to its recency. As performances of this task depend highly on the dataset, experiments using different private datasets are not directly comparable. Therefore, in this paper we propose ASNets, a benchmark dataset with two sets of aligned social networks. With this dataset, we can now properly evaluate different approaches and compare them fairly. The two sets of aligned networks have 328,224 and 141,614 aligned users respectively, covering multilingual usage (Chinese and English) and various types of social networks including general purposed networks, review sites and microblogging sites. We describe the collecting methodology and statistics in details, and evaluate several state-of-the-art network aligning approaches. Beside introducing the dataset, we further propose several potential research directions that benefit from ASNets.

Learning and predicting user responses, such as clicks and conversions, are crucial for many Internet-based businesses including web search, e-commerce, and online advertising. Typically, a user response model is established by optimizing the prediction accuracy, e.g., minimizing the error between the prediction and the ground truth user response. However, in many practical cases, predicting user responses is only part of a rather larger predictive or optimization task, where on one hand, the accuracy of a user response prediction determines the final (expected) utility to be optimized, but on the other hand, its learning may also be influenced from the follow-up stochastic process. It is, thus, of great interest to optimize the entire process as a whole rather than treat them independently or sequentially. In this paper, we take real-time display advertising as an example, where the predicted user's ad click-through rate (CTR) is employed to calculate a bid for an ad impression in the second price auction. We reformulate a common logistic regression CTR model by putting it back into its subsequent bidding context: rather than minimizing the prediction error, the model parameters are learned directly by optimizing campaign profit. The gradient update resulted from our formulations naturally fine-tunes the cases where the market competition is high, leading to a more cost-effective bidding. Our experiments demonstrate that, while maintaining comparable CTR prediction accuracy, our proposed user response learning leads to campaign profit gains as much as 78.2% for offline test and 25.5% for online A/B test over strong baselines.

Predicting user responses, such as clicks and conversions, is of great importance and has found its usage inmany Web applications including recommender systems, websearch and online advertising. The data in those applicationsis mostly categorical and contains multiple fields, a typicalrepresentation is to transform it into a high-dimensional sparsebinary feature representation via one-hot encoding. Facing withthe extreme sparsity, traditional models may limit their capacityof mining shallow patterns from the data, i.e. low-order featurecombinations. Deep models like deep neural networks, on theother hand, cannot be directly applied for the high-dimensionalinput because of the huge feature space. In this paper, we proposea Product-based Neural Networks (PNN) with an embeddinglayer to learn a distributed representation of the categorical data, a product layer to capture interactive patterns between interfieldcategories, and further fully connected layers to explorehigh-order feature interactions. Our experimental results on twolarge-scale real-world ad click datasets demonstrate that PNNsconsistently outperform the state-of-the-art models on various metrics.

An accurate and comprehensive user modeling technique is crucial for the quality of recommender systems. Traditionally, we model user preferences using only actions from the target site and may suffer from cold-start problem. As nowadays people normally engage in multiple online sites for various needs, we consider leveraging the cross-site actions to improve the user modeling accuracy. Specifically, in this paper we aim at achieving a more comprehensive and accurate user modeling by modeling user's actions in multiple aligned heterogeneous sites simultaneously. To do so, we propose a modularized probabilistic graphical model framework JUMA. We further integrate topic model and matrix factorization into JUMA for joint user modeling over text-based and item-based sites. We assemble and publish large-scale dataset for comprehensive analyzing and evaluation. Experimental results show that our framework JUMA out performs traditional within-site user modeling techniques, especially for cold-start scenarios. For cold-start users, we achieve relative improvements of 9.3% and 12.8% comparing to existing within-site approaches for recommendation in item-based and text-based sites respectively. Thus we draw the conclusion that aligning heterogeneous sites and modeling users jointly do help to improve the quality of online recommender systems.

Conformity has a strong influence to user behaviors, even in online environment. When surfing online, users are usually flooded with others' opinions. These opinions implicitly contribute to the user's ongoing behaviors. However, there is no research work modeling online conformity yet. In this paper, we model user's conformity in online rating sites. We conduct analysis using real data to show the existence and strength of conformity in these scenarios. We propose a matrix-factorization-based conformity modeling technique to improve the accuracy of rating prediction. Experiments show that our model outperforms existing works significantly (with a relative improvement of 11.72% on RMSE). Therefore, we draw the conclusion that conformity modeling is important for understanding user behaviors and can contribute to further improve the online recommender systems.

Online review sites are widely used for various domains including movies and restaurants. These sites now have strong influences towards users during purchasing processes. There exist plenty of research works for review sites on various aspects, including item recommendation, user behavior analysis, etc. However, due to the lack of complete and comprehensive dataset, there are still problems that remain to be solved. Therefore, in this paper we assemble and publish such dataset (CCMR) for the community. CCMR outruns existing datasets in terms of completeness, comprehensiveness and scale. Besides describing the dataset and its collecting methodology, we also propose several potential research topics that are made possible by having this dataset. Such topics include: (i) a statistical approach to reduce the impacts from fake reviews and (ii) analyzing and modeling the influences of public opinions towards users during rating actions. We further conduct preliminary analysis and experiments for both directions to show that they are promising.

State-of-the-art methods for product recommendation encounter a significant performance drop in categories where a user has no purchase history. This problem needs to be addressed since current online retailers are moving beyond single category and attempting to be diversified. In this article, we investigate the challenging problem of product recommendation in unexplored categories and discover that the price, a factor comparable across categories, can improve the recommendation performance significantly. We introduce the price utility concept to characterize users’ sense of price and propose three different utility functions. We show that user price preference in a category is a distribution and we mine typical user price preference patterns based on three different types of distance between distributions. We fuse user price preference through regularization and joint factorization to boost recommendation performance in both browsing and buying shopping orientations. Experimental results show that fusing user price preference improves performance in a series of recommendation tasks: unexplored category recommendation, product recommendation under a given unexplored category, and product recommendation under generic unexplored categories.

The collective anomaly denotes a collection of nearby locations that are anomalous during a few consecutive time intervals in terms of phenomena collectively witnessed by multiple datasets. The collective anomalies suggest there are underlying problems that may not be identified based on a single data source or in a single location. It also associates individual locations and time intervals, formulating a panoramic view of an event. To detect a collective anomaly is very challenging, however, as different datasets have different densities, distributions, and scales. Additionally, to find the spatio-temporal scope of a collective anomaly is time consuming as there are many ways to combine regions and time slots. Our method consists of three components: Multiple-Source Latent-Topic (MSLT) model, Spatio-Temporal Likelihood Ratio Test (ST_LRT) model, and a candidate generation algorithm. MSLT combines multiple datasets to infer the latent functions of a geographic region in the framework of a topic model. In turn, a region's latent functions help estimate the underlying distribution of a sparse dataset generated in the region. ST_LRT learns a proper underlying distribution for different datasets, and calculates an anomalous degree for each dataset based on a likelihood ratio test (LRT). It then aggregates the anomalous degrees of different datasets, using a skyline detection algorithm. We evaluate our method using five datasets related to New York City (NYC): 311 complaints, taxicab data, bike rental data, points of interest, and road network data, finding the anomalies that cannot be identified (or earlier than those detected) by a single dataset. Results show the advantages beyond six baseline methods.

In this paper, we notice that sparse and low-rank structures arise in the context of many collaborative filtering applications where the underlying graphs have block-diagonal adjacency matrices. Therefore, we propose a novel Sparse and Low-Rank Linear Method (Lor SLIM) to capture such structures and apply this model to improve the accuracy of the Top-N recommendation. Precisely, a sparse and low-rank aggregation coefficient matrix W is learned from Lor SLIM by solving an l1-norm and nuclear norm regularized optimization problem. We also develop an efficient alternating augmented Lagrangian method (ADMM) to solve the optimization problem. A comprehensive set of experiments is conducted to evaluate the performance of Lor SLIM. The experimental results demonstrate the superior recommendation quality of the proposed algorithm in comparison with current state-of-the-art methods.

Many tasks in data mining and related fields can be formalized as matching between objects in two heterogeneous domains, including collaborative filtering, link prediction, image tagging, and web search. Machine learning techniques, referred to as learning-to-match in this paper, have been successfully applied to the problems. Among them, a class of state-of-the-art methods, named feature-based matrix factorization, formalize the task as an extension to matrix factorization by incorporating auxiliary features into the model. Unfortunately, making those algorithms scale to real world problems is challenging, and simple parallelization strategies fail due to the complex cross talking patterns between sub-tasks. In this paper, we tackle this challenge with a novel parallel and efficient algorithm. Our algorithm, based on coordinate descent, can easily handle hundreds of millions of instances and features on a single machine. The key recipe of this algorithm is an iterative relaxation of the objective to facilitate parallel updates of parameters, with guaranteed convergence on minimizing the original objective function. Experimental results demonstrate that the proposed method is effective on a wide range of matching problems, with efficiency significantly improved upon the baselines while accuracy retained unchanged.

This paper instantly infers the gas consumption and pollution emission of vehicles traveling on a city's road network in a current time slot, using GPS trajectories from a sample of vehicles (e.g., taxicabs). The knowledge can be used to suggest cost-efficient driving routes as well as identifying road segments where gas has been wasted significantly. The instant estimation of the emissions from vehicles can enable pollution alerts and help diagnose the root cause of air pollution in the long run. In our method, we first compute the travel speed of each road segment using the GPS trajectories received recently. As many road segments are not traversed by trajectories (i.e., data sparsity), we propose a Travel Speed Estimation (TSE) model based on a context-aware matrix factorization approach. TSE leverages features learned from other data sources, e.g., map data and historical trajectories, to deal with the data sparsity problem. We then propose a Traffic Volume Inference (TVI) model to infer the number of vehicles passing each road segment per minute. TVI is an unsupervised Bayesian Network that incorporates multiple factors, such as travel speed, weather conditions and geographical features of a road. Given the travel speed and traffic volume of a road segment, gas consumption and emissions can be calculated based on existing environmental theories. We evaluate our method based on extensive experiments using GPS trajectories generated by over 32,000 taxis in Beijing over a period of two months. The results demonstrate the advantages of our method over baselines, validating the contribution of its components and finding interesting discoveries for the benefit of society.

State-of-the-art methods for product recommendation encounter significant performance drop in categories where a user has no purchase history. This problem needs to be addressed since current online retailers are moving beyond single category and attempting to be diversified. In this paper, we investigate the challenge problem of product recommendation in unexplored categories and discover that the price, a factor transferrable across categories, can improve the recommendation performance significantly. Through our investigation, we address four research questions progressively: 1) what is the impact of unexplored category on recommendation performance? 2) How to represent the price factor from the recommendation point of view? 3) What does price factor across categories mean to recommendation? 4) How to utilize price factor across categories for recommendation in unexplored categories? Based on a series of experiments and analysis conducted on a dataset collected from a leading E-commerce website, we discover valuable findings for the above four questions: first, unexplored categories cause performance drop by 40% relatively for current recommendation systems; second, the price factor can be represented as either a quantity for a product or a distribution for a user to improve performance; third, consumer behavior with respect to price factor across categories is complicated and needs to be carefully modeled; finally and most importantly, we propose a new method which encodes the two perspectives of the price factor. The proposed method significantly improves the recommendation performance in unexplored categories over the state-of-the-art baseline systems and shortens the performance gap by 43% relatively.

Topic models have been widely used for text analysis. Previous topic models have enjoyed great success in mining the latent topic structure of text documents. With many efforts made on endowing the resulting document-topic distributions with different motivations, however, none of these models have paid any attention on the resulting topic-word distributions.Since topic-word distribution also plays an important role in the modeling performance,topic models which emphasize only the resulting document-topic representations but pay less attention to the topic-term distributions are limited. In this paper, we propose the Orthogonalized Topic Model(OTM) which imposes an orthogonality constraint on the topic-term distributions. We also propose a novel model fitting algorithm based on the generalized Expectation-Maximization algorithm and the Newthon-Raphson method. Quantitative evaluation of text classification demonstrates that OTM outperforms other baseline models and indicates the important role played by topic orthogonalizing.

Differential privacy (DP) enables publishing statistical query results over sensitive data, with rigorous privacy guarantees, and very conservative assumptions about the adversary's background knowledge. This paper focuses on the interactive DP framework, which processes incoming queries on the fly, each of which consumes a portion of the user-specified privacy budget. Existing systems process each query independently, which often leads to considerable privacy budget waste. Motivated by this, we propose Pioneer, a query optimizer for an interactive, DP-compliant DBMS. For each new query, Pioneer creates an execution plan that combines past query results and new results from the underlying data. When a query has multiple semantically equivalent plans, Pioneer automatically selects one with minimal privacy budget consumption. Extensive experiments confirm that Pioneer achieves significant savings of the privacy budget, and can answer many more queries than existing systems for a fixed total budget, with comparable result accuracy.

In the field of recommendation system research, a key challenge is how to effectively recommend items for new users, a problem generally known as cold-start recommendation. In order to alleviate cold-start problem, recently systems try to get the users' interests by progressively querying users' preference on predefined items. Constructing the query process via machine learning based techniques becomes an important direction to solve cold-start problem. In this paper, we propose a novel interview process learning algorithm. Different from previous approaches which focus on rate prediction, our model is able to handle wide ranges of loss functions and can be used in collaborative ranking task. Experimental results on three real world recommendation dataset demonstrate that our proposed method outperforms several baseline methods.

Many Internet users have encountered serious information overload problem on social networks such as Facebook and Twitter, where users can consume the streams of social updates from their social connections. Traditional methods solving this problem include collaborative filtering and information diffusion modeling. Both methods answer the "who will adopt what" question from different perspective, while either of them only captures single-faceted knowledge of evidences. In this paper, we solve the personalized social update recommendation problem by proposing a framework which integrates the advantages of collaborative filtering and the characteristics of diffusion processes. The main contributions of this paper are three folds. First, we propose a plenty of diffusion features which capture the characteristics of diffusion processes. Second, we build a joint model which takes the advantages of both collaborative filtering and the characteristics of diffusion processes for recommendation. Finally, experiments on two real-world datasets show that our joint model outperforms the methods capturing single-faceted knowledge and several other baselines.

In this paper, we propose a set-oriented personalized ranking model for diversified top-N recommendation. Users may have various individual ranges of interests. For personalized top-N recommendation task, the combination of relevance and diversity in recommendation results would be desirable. For this purpose, we integrate the concept of diversity into traditional matrix factorization model to construct a set-oriented collaborative filtering model. By optimizing this model with a set-oriented pairwise ranking method, we directly achieve personalized top-N recommendation results which are both relevant and diversified. We also utilize category information explicitly for learning personalized diversity. Experimental results show that our model outperforms traditional models in terms of personalized diversity and maintains good performance on relevance prediction.

Collaborative filtering techniques rely on aggregated user preference data to make personalized predictions. In many cases, users are reluctant to explicitly express their preferences and many recommender systems have to infer them from implicit user behaviors, such as clicking a link in a webpage or playing a music track. The clicks and the plays are good for indicating the items a user liked (i.e., positive training examples), but the items a user did not like (negative training examples) are not directly observed. Previous approaches either randomly pick negative training samples from unseen items or incorporate some heuristics into the learning model, leading to a biased solution and a prolonged training period. In this paper, we propose to dynamically choose negative training samples from the ranked list produced by the current prediction model and iteratively update our model. The experiments conducted on three large-scale datasets show that our approach not only reduces the training time, but also leads to significant performance gains.

We propose Resa, a novel framework for robust, elastic and realtime stream processing in the cloud. In addition to traditional functionalities of streaming and cloud systems, Resa provides (i) a novel mechanism that handles dynamic additions and removals nodes in an operator, and (ii) a node re-assignment scheme that minimizes output latency using a queuing model. We have implemented Resa on top of Twitter Storm. Experiments using real data demonstrate the effectiveness and efficiency of Resa.

Many previous research works have focused on analyzing online social networks in many dimensions, as they bring large commercial value and provide significant references for many other subjects. Pinterest, a pinboard-style image sharing social service, has attracted much attention recently and become one of the most popular social networks. The special mechanism and style of Pinterest distinguish it from other previous popular social networks and shape totally different user behaviors, which makes it worth launching a new study on Pinterest. In this paper, we have an empirical study of user behaviors on Pinterest, based on a large Pinterest dataset containing 1.13 million users, 57 million following relations, 19 million boards and 933 million pins. We focus on studying the characteristics, manifestations and overall effects of user behaviors from many aspects, including the user interests, correlations between neighboring users, the common features of the most popular users, the topology of the network structure, etc. The most distinguishing characteristic of Pinterest is that users focus on everyday lives and are willing to collect many images about decoration, food, fashion, etc, which makes Pinterest an ideal advertising and marketing platform for retail companies. Many other qualitative and quantitative analysis on user behaviors have been discussed in our paper. We provide a comprehensive understanding of user behaviors on the Pinterest social network, which is our main contribution.

With the ever-growing use of textual biomedical data, domain entity annotation has become very important in biomedicine. Previous works on annotating domain entities from biomedical references suffer from several issues, such as a data flexibility problem, language dependency, and limitations with respect to word sense disambiguation. Meanwhile, the Linked Open Data (LOD) Initiative aims at interlinking data from various open knowledge bases. The numbers of entities and properties describing semantic relationships between entities within the linked data cloud have become very large. In this paper, we propose a knowledge-incentive approach for entity annotation in biomedicine, and present Me Detect, a prototype system that we developed based on this approach. With this approach, we over-come the problems of previous works using LOD-based collective annotation. Finally, we present the results of experiments that verify the effectiveness and efficiency of our approach.

Publishing structured data and linking them to Linking Open Data (LOD) is an ongoing effort to create a Web of data. Each newly involved data source may contain duplicated instances (entities) whose descriptions or schemata differ from those of the existing sources in LOD. To tackle this heterogeneity issue, several matching methods have been developed to link equivalent entities together. Many general-purpose matching methods which focus on similarity metrics suffer from very diverse matching results for different data source pairs. On the other hand, the dataset-specific ones leverage heuristic rules or even manual efforts to ensure the quality, which makes it impossible to apply them to other sources or domains. In this paper, we offer a third choice, a general method of automatically discovering dataset-specific matching rules. In particular, we propose a semi-supervised learning algorithm to iteratively refine matching rules and find new matches of high confidence based on these rules. This dramatically relieves the burden on users of defining rules but still gives high-quality matching results. We carry out experiments on real-world large scale data sources in LOD; the results show the effectiveness of our approach in terms of the precision of discovered matches and the number of missing matches found. Furthermore, we discuss several extensions (like similarity embedded rules, class restriction and SPARQL rewriting) to fit various applications with different requirements.

This paper is concerned with the joint allocation of bid price and campaign budget in sponsored search. In this application, an advertiser can create a number of campaigns and set a budget for each of them. In a campaign, he/she can further create several ad groups with bid keywords and bid prices. Data analysis shows that many advertisers are dealing with a very large number of campaigns, bid keywords, and bid prices at the same time, which poses a great challenge to the optimality of their campaign management. As a result, the budgets of some campaigns might be too low to achieve the desired performance goals while those of some other campaigns might be wasted; the bid prices for some keywords may be too low to win competitive auctions while those of some other keywords may be unnecessarily high. In this paper, we propose a novel algorithm to automatically address this issue. In particular, we model the problem as a constrained optimization problem, which maximizes the expected advertiser revenue subject to the constraints of the total budget of the advertiser and the ranges of bid price change. By solving this optimization problem, we can obtain an optimal budget allocation plan as well as an optimal bid price setting. Our simulation results based on the sponsored search log of a commercial search engine have shown that by employing the proposed method, we can effectively improve the performances of the advertisers while at the same time we also see an increase in the revenue of the search engine. In addition, the results indicate that this method is robust to the second-order effects caused by the bid fluctuations from other advertisers.

Digital music has experienced a quite fascinating transformation during the past decades. Thousands of people share or distribute their music collections on the Internet, resulting in an explosive increase of information and more user dependence on automatic recommender systems. Though there are many techniques such as collaborative filtering, most approaches focus mainly on users' global behaviors, neglecting local actions and the specific properties of music. In this paper, we propose a simple and effective local implicit feedback model mining users' local preferences to get better recommendation performance in both rating and ranking prediction. Moreover, we design an efficient training algorithm to speed up the updating procedure, and give a method to find the most appropriate time granularity to assist the performance. We conduct various experiments to evaluate the performance of this model, which show that it outperforms baseline model significantly. Integration with existing temporal models achieves a great improvement compared to the reported best single model for Yahoo! Music.

In recent years, more and more images have been uploaded and published on the Web. Along with text Web pages, images have been becoming important media to place relevant advertisements. Visual contextual advertising, a young research area, refers to finding relevant text advertisements for a target image without any textual information (e.g., tags). There are two existing approaches, advertisement search based on image annotation, and more recently, advertisement matching based on feature translation between images and texts. However, the state of the art fails to achieve satisfactory results due to the fact that recommended advertisements are syntactically matched but semantically mismatched. In this paper, we propose a semantic approach to improving the performance of visual contextual advertising. More specifically, we exploit a large high-quality image knowledge base (ImageNet) and a widely-used text knowledge base (Wikipedia) to build a bridge between target images and advertisements. The image-advertisement match is built by mapping images and advertisements into the respective knowledge bases and then finding semantic matches between the two knowledge bases. The experimental results show that semantic match outperforms syntactic match significantly using test images from Flickr. We also show that our approach gives a large improvement of 16.4% on the precision of the top 10 matches over previous work, with more semantically relevant advertisements recommended.

Twitter has rapidly grown to a popular social network in recent years and provides a large number of real-time messages for users. Tweets are presented in chronological order and users scan the followees' timelines to find what they are interested in. However, an information overload problem has troubled many users, especially those with many followees and thousands of tweets arriving every day. In this paper, we focus on recommending useful tweets that users are really interested in personally to reduce the users' effort to find useful information. Many kinds of information on Twitter are available for helping recommendation, including the user's own tweet history, retweet history and social relations between users. We propose a method of making tweet recommendations based on collaborative ranking to capture personal interests. It can also conveniently integrate the other useful contextual information. Our final method considers three major elements on Twitter: tweet topic level factors, user social relation factors and explicit features such as authority of the publisher and quality of the tweet. The experiments show that all the proposed elements are important and our method greatly outperforms several baseline methods.

With the rapid growing of Web 2.0, people spend more time on social networks such as Facebook and Twitter. In order to know the people they are interacting with, finding the web appearances of them will help the social network users to a great extent. We propose a novel and effective latent factor model to find web appearances of target social network users. Our method solves the name ambiguity problem by simultaneously exploring the link structure of social networks and the web. Experiments on real-world data show the superiority of our method over several baselines.

Recently, recommender systems have fascinated researchers and benefited a variety of people's online activities, enabling users to survive the explosive web information. Traditional collaborative filtering techniques handle the general recommendation well. However, most such approaches usually focus on long term preferences. To discover more short term factors influencing people's decisions, we propose a short term preferences model, implemented with implicit user feedback. We conduct experiments comparing the performances of different short term models, which show that our model outperforms significantly compared to those long term models.

e-differential privacy (e-DP) is a strong and rigorous scheme for protecting individuals' privacy while releasing useful statistical information. The main idea is to inject random noise into the results of statistical queries, such that the existence of any single record has negligible impact on the distributions of query results. The accuracy of such randomized results depends heavily upon the query processing technique, which has been an active research topic in recent years. So far, most existing methods focus on 1-dimensional queries. The only work that handles multi-dimensional query processing under e-DP is [1], which indexes the sensitive data using variants of the quad-tree and the k-d-tree. As we point out in this paper, these structures are inherently suboptimal for answering queries under e-DP. Consequently, the solutions in [1] suffer from several serious drawbacks, including limited and unstable query accuracy, as well as bias towards certain types of queries. Motivated by this, we propose the DP-tree, a novel index structure for multi-dimensional query processing under e-DP that eliminates the problems encountered by the methods in [1]. Further, we show that the effectiveness of the DP-tree can be improved using statistical information about the query workload. Extensive experiments using real and synthetic datasets confirm that the DP-tree achieves significantly higher query accuracy than existing methods. Interestingly, an adaptation of the DP-tree also outperforms previous 1D solutions in their restricted scope, by large margins.

Serendipitous recommendation has benefitted both e-retailers and users. It tends to suggest items which are both unexpected and useful to users. These items are not only profitable to the retailers but also surprisingly suitable to consumers' tastes. However, due to the imbalance in observed data for popular and tail items, existing collaborative filtering methods fail to give satisfactory serendipitous recommendations. To solve this problem, we propose a simple and effective method, called serendipitous personalized ranking. The experimental results demonstrate that our method significantly improves both accuracy and serendipity for top-N recommendation compared to traditional personalized ranking methods in various settings.

Wikipedia, one of the best-known wikis and the world’s largest free online encyclopedia, has embraced the power of collaborative editing to harness collective intelligence. However, using such a wiki to create high-quality articles is not as easy as people imagine, given for instance the difficulty of reusing knowledge already available in Wikipedia. As a result, the heavy burden of upbuilding and maintaining the ever-growing online encyclopedia still rests on a small group of people. In this article, we aim at facilitating wiki authoring by providing annotation recommendations, thus lightening the burden of both contributors and administrators. We leverage the collective wisdom of the users by exploiting Semantic Web technologies with Wikipedia data and adopt a unified algorithm to support link, category, and semantic relation recommendation. A prototype system named EachWiki is proposed and evaluated. The experimental results show that it has achieved considerable improvements in terms of effectiveness, efficiency and usability. The proposed approach can also be applied to other wiki-based collaborative editing systems.

This paper is concerned with the problem of mining social emotions from text. Recently, with the fast development of web 2.0, more and more documents are assigned by social users with emotion labels such as happiness, sadness, and surprise. Such emotions can provide a new aspect for document categorization, and therefore help online users to select related documents based on their emotional preferences. Useful as it is, the ratio with manual emotion labels is still very tiny comparing to the huge amount of web/enterprise documents. In this paper, we aim to discover the connections between social emotions and affective terms and based on which predict the social emotion from text content automatically. More specifically, we propose a joint emotion-topic model by augmenting Latent Dirichlet Allocation with an additional layer for emotion modeling. It first generates a set of latent topics from emotions, followed by generating affective terms from each topic. Experimental results on an online news collection show that the proposed model can effectively identify meaningful latent topics for each emotion. Evaluation on emotion prediction further verifies the effectiveness of the proposed model.

With the rapid growth of social Web applications such as Twitter and online advertisements, the task of understanding short texts is becoming more and more important. Most traditional text mining techniques are designed to handle long text documents. For short text messages, many of the existing techniques are not effective due to the sparseness of text representations. To understand short messages, we observe that it is often possible to find topically related long texts, which can be utilized as the auxiliary data when mining the target short texts data. In this article, we present a novel approach to cluster short text messages via transfer learning from auxiliary long text data. We show that while some previous work exists that enhance short text clustering with related long texts, most of them ignore the semantic and topical inconsistencies between the target and auxiliary data and hurt the clustering performance. To accommodate the possible inconsistency between source and target data, we propose a novel topic model - Dual Latent Dirichlet Allocation (DLDA) model, which jointly learns two sets of topics on short and long texts and couples the topic parameters to cope with the potential inconsistency between data sets. We demonstrate through large-scale clustering experiments on both advertisements and Twitter data that we can obtain superior performance over several state-of-art techniques for clustering short text documents.

This paper studies the problem of prominent streak discovery in sequence data. Given a sequence of values, a prominent streak is a long consecutive subsequence consisting of only large (small) values. For finding prominent streaks, we make the observation that prominent streaks are skyline points in two dimensions- streak interval length and minimum value in the interval. Our solution thus hinges upon the idea to separate the two steps in prominent streak discovery' candidate streak generation and skyline operation over candidate streaks. For candidate generation, we propose the concept of local prominent streak (LPS). We prove that prominent streaks are a subset of LPSs and the number of LPSs is less than the length of a data sequence, in comparison with the quadratic number of candidates produced by a brute-force baseline method. We develop efficient algorithms based on the concept of LPS. The non-linear LPS-based method (NLPS) considers a superset of LPSs as candidates, and the linear LPS-based method (LLPS) further guarantees to consider only LPSs. The results of experiments using multiple real datasets verified the effectiveness of the proposed methods and showed orders of magnitude performance improvement against the baseline method.

In recent years, online shopping is becoming more and more popular. Users type keyword queries on product search systems to find relevant products, accessories, and even related products. However, existing product search systems always return very similar products on the first several pages instead of taking diversity into consideration. In this paper, we propose a novel approach to address the diversity issue in the context of product search. We transform search result diversification into a combination of diversifying product categories and diversifying product attribute values within each category. The two sub-problems are optimization problems which can be reduced into well-known NP-hard problems respectively. We further leverage greedy-based approximation algorithms for efficient product search results re-ranking.

No abstract available.

Recently, more and more short texts (e.g., ads, tweets) appear on the Web. Classifying short texts into a large taxonomy like ODP or Wikipedia category system has become an important mining task to improve the performance of many applications such as contextual advertising and topic detection for micro-blogging. In this paper, we propose a novel multi-stage classification approach to solve the problem. First, explicit semantic analysis is used to add more features for both short texts and categories. Second, we leverage information retrieval technologies to fetch the most relevant categories for an input short text from thousands of candidates. Finally, a SVM classifier is applied on only a few selected categories to return the final answer. Our experimental results show that the proposed method achieved significant improvements on classification accuracy compared with several existing state of art approaches.

Community discovery on large-scale linked document corpora has been a hot research topic for decades. There are two types of links. The first one, which we call d2d-link, indicates connectiveness among different documents, such as blog references and research paper citations. The other one, which we call u2u-link, represents co-occurrences or simultaneous participations of different users in one document and typically each document from u2u-link corpus has more than one user/author. Examples of u2u-link data covers email archives and research paper co-authorship networks. Community discovery in d2d-link data has achieved much success, while methods for that in u2u-link data either make no use of the textual content of the documents or make oversimplified assumptions about the users and the textual content. In this paper we propose a general approach of community discovery for u2u-link data, i.e., multiple user data, by placing topical variables on multiple authors' participations in documents. Experiments on a research proceeding co-authorship corpus and a New York Times news corpus show the effectiveness of our model.

In this paper, we propose fuzzy pD* semantics which generalizes pD* semantics to reason over fuzzy RDF data using OWL vocabulary. We first define the notions of fuzzy RDF graph and fuzzy pD* interpretation. We then present a set of fuzzy pD*entailment rules and define the Best Degree Bound (BDB) of a triple derived from a fuzzy RDF graph. We show the existence of the BDB of an arbitrary triple. After that, we generalize the partial and full pD* closures to obtain the BDBs of derived triples. We show that the partial fuzzy closure exists and can be computed within polynomial time. Finally, we prove soundness and completeness results for the entailment relation. We also prove that the consistency checking is in P, the entailment is NP-complete, and in P if the target fuzzy RDF graph is ground. Therefore, extending the pD* semantics with fuzzy semantics does not increase the computational complexity.

It is well-known that textual information such as video transcripts and video reviews can significantly enhance the performance of video summarization algorithms. Unfortunately, many videos on the Web such as those from the popular video sharing site YouTube do not have useful textual information. The goal of this paper is to propose a transfer learning framework for video summarization: in the training process both the video features and textual features are exploited to train a summarization algorithm while for summarizing a new video only its video features are utilized. The basic idea is to explore the transferability between videos and their corresponding textual information. Based on the assumption that video features and textual features are highly correlated with each other, we can transfer textual information into knowledge on summarization using video information only. In particular, we formulate the video summarization problem as that of learning a mapping from a set of shots of a video to a subset of the shots using the general framework of SVM-based structured learning. Textual information is transferred by encoding them into a set of constraints used in the structured learning process which tend to provide a more detailed and accurate characterization of the different subsets of shots. Experimental results show significant performance improvement of our approach and demonstrate the utility of textual information for enhancing video summarization.

In this article, we address the problem of question clustering and study its use for re-ranking question search results. In question clustering we have to organize question search results into certain meaningful and condensed groups. Specifically, we propose to use a data structure consisting of question topic and question focus for modeling questions, and then cluster questions on the basis of the data structure. Experimental results show that our approach to question clustering improves the performance of question search significantly better than the approach not utilizing the topic–focus structure.

As more and more multimedia data become available on the Web, mining on those data is playing an increasingly important role in Web applications. In this paper, we investigate the interplay between multimedia data mining and text data mining. Specifically, in an approach we called text-aided image classification (TAIC), we address the problem of image classification with very limited amount of labeled images and a large amount of auxiliary labeled text data. This problem is important in practice, since currently on the Web, labeled text data are usually much more than image data. To solve the problem, based on the “bag-of-words” view and the Naive Bayes classification model, we focus our attention on the estimation of the image feature distribution under given concept. We extend the Naive Bayes algorithm by considering a mapping that maps the most discriminative text features into the image feature space. This feature mapping is estimated based on the text-image cooccurrence data on the Web, acting like a bridge that connects text and image knowledge. With this process, we estimate target image feature distribution from a text model based on sufficient labeled data. Our empirical results on real world data sets show that our method makes a good approximation of the image feature distribution when trained with abundant labeled images. In the case amount of labeled images is very limited, the classification performance is improved by using auxiliary labeled text data, which shows that our method can indeed integrate text and image knowledge in a simple yet effective way.

This paper is concerned with community discovery in textual interaction graph, where the links between entities are indicated by textual documents. Specifically, we propose a Topical Link Model(TLM), which leverages Hierarchical Dirichlet Process(HDP) to introduce hidden topical variable of the links. Other than the use of links, TLM can look into the documents on the links in detail to recover sound communities. Moreover, TLM is a nonparametric model, which is able to learn the number of communities from the data. Extensive experiments on two real world corpora show TLM outperforms two state-of-the-art baseline models, which verify the effectiveness of TLM in determining the proper number of communities and generating sound communities.

With the development of Semantic Web in recent years, an increasing amount of semantic data has been created in form of Resource Description Framework (RDF). Current visualization techniques help users quickly understand the underlying RDF data by displaying its structure in an overview. However, detailed information can only be accessed by further navigation. An alternative approach is to display the global context as well as the local details simultaneously in a unified view. This view supports the visualization and navigation on RDF data in an integrated way. In this demonstration, we present ZoomRDF, a framework that: i) adapts a space-optimized visualization algorithm for RDF, which allows more resources to be displayed, thus maximizes the utilization of display space, ii) combines the visualization with a fisheye zooming concept, which assigns more space to some individual nodes while still preserving the overview structure of the data, iii) considers both the importance of resources and the user interaction on them, which offers more display space to those elements the user may be interested in. We implement the framework based on the Gene Ontology and demonstrate that it facilitates tasks like RDF data exploration and editing.

It is often difficult and time-consuming to provide a large amount of positive and negative examples for training a classification system in many applications such as information retrieval. Instead, users often find it easier to indicate just a few positive examples of what he or she likes, and thus, these are the only labeled examples available for the learning system. A large amount of unlabeled data are easier to obtain. How to make use of the positive and unlabeled data for learning is a critical problem in machine learning and information retrieval. Several approaches for solving this problem have been proposed in the past, but most of these methods do not work well when only a small amount of labeled positive data are available. In this paper, we propose a novel algorithm called Topic-Sensitive pLSA to solve this problem. This algorithm extends the original probabilistic latent semantic analysis (pLSA), which is a purely unsupervised framework, by injecting a small amount of supervision information from the user. The supervision from users is in the form of indicating which documents fit the users' interests. The supervision is encoded into a set of constraints. By introducing the penalty terms for these constraints, we propose an objective function that trades off the likelihood of the observed data and the enforcement of the constraints. We develop an iterative algorithm that can obtain the local optimum of the objective function. Experimental evaluation on three data corpora shows that the proposed method can improve the performance especially only with a small amount of labeled positive data.

This paper is concerned with the study of information retrieval (IR) on Accumulative Social Descriptions (ASDs). ASDs refer to Web texts that accumulated by many Web users describing certain Web resources, such as anchor texts, search logs and social annotations. There have been some studies working on leveraging ASDs for improving search performance in both internet and intranet. However, to the best of our knowledge, no prior study has concerned the specific generation features of ASDs, which are the focus point of this paper. Specifically, we consider the generation features from two perspectives, the generation processes and the generated distributions. Further, three probabilistic IR models are derived based on them. The three models are first demonstrated with one toy dataset and then empirically evaluated with two real datasets: an internet dataset consisting of 90,295 Web pages, with 25,845,818 social annotations crawled from Del.icio.us and 31,320,005 pieces of anchor texts crawled through Yahoo! API, and an intranet dataset consisting of 179,835 Web pages with 1,245,522 annotations dumped from the intranet tagging system in IBM, named as Dogear. Extensive experimental results show that the proposed methods, which fully leverage the generation features of ASDs, improve the performance of both internet and intranet search significantly.

Web document could be seen to be composed of textual content as well as social metadata of various forms (e.g., anchor text, search query and social annotation), both of which are valuable to indicate the semantic content of the document. However, due to the free nature of the web, the two streams of web data suffer from the serious problems of noise and sparseness, which have actually become the major challenges to the success of many web mining applications. Previous work has shown that it could enhance the content of web document by integrating anchor text and search query. In this paper, we study the problem of exploring emergent social annotation for document enhancement and propose a novel reinforcement framework to generate "social representation" of document. Distinguishing from prior work, textual content and social annotation are enhanced simultaneously in our framework, which is achieved by exploiting a kind of mutual reinforcement relationship behind them. Two convergent models, social content model and social annotation model, are symmetrically derived from the framework to represent enhanced textual content and enhanced social annotation respectively. The enhanced document is referred to as Social Document or sDoc in that it could embed complementary viewpoints from many web authors and many web visitors. In this sense, the document semantics is enhanced exactly by exploring social wisdom. We build the framework on a large Del.icio.us data and evaluate it through three typical web mining applications: annotation, classification and retrieval. Experimental results demonstrate that social representation of web document could boost the performance of these applications significantly.

This paper is concerned with the problem of social affective text mining, which aims to discover the connections between social emotions and affective terms based on user-generated emotion labels. We propose a joint emotion-topic model by augmenting latent Dirichlet allocation with an additional layer for emotion modeling. It first generates a set of latent topics from emotions, followed by generating affective terms from each topic. Experimental results on an online news collection show that the proposed model can effectively identify meaningful latent topics for each emotion. Evaluation on emotion prediction further verifies the effectiveness of the proposed model.

Online advertising represents a growing part of the revenues of ma-jor Internet service providers such as Google and Yahoo. A com-monly used strategy is to place advertisements (ads) on the search result pages according to the users ’ submitted queries. Relevant ads are likely to be clicked by a user and to increase the revenues of both advertisers and publishers. However, bid phrases defined by ad-owners are usually contained in limited number of ads. Directly matching user queries with bid phrases often results in finding few appropriate ads. To address this shortcoming, query expansion is often used to increase the chances to match the ads. Nevertheless, query expansion on top of the traditional inverted index faces ef-ficiency issues such as high time complexity and heavy I/O costs. Moreover, precision cannot always be improved, sometimes even hurt due to the involvement of additional noise.

The Web as a global information space is developing from a Web of documents to a Web of data. This development opens new ways for addressing complex information needs. Search is no longer limited to matching keywords against documents, but instead complex information needs can be expressed in a structured way, with precise answers as results. In this paper, we demonstrate Hermes, an infrastructure for data web search. To provide an end-user oriented interface, we support expressive keyword search by translating user information needs into structured queries. We integrate heterogeneous web data sources with automatically computed mappings. Schema-level mappings are exploited in constructing structured queries against the integrated schema. These structured queries are decomposed into queries against the local web data sources, which are then processed in a distributed way.

Document summarization plays an increasingly important role with the exponential growth of documents on the Web. Many supervised and unsupervised approaches have been proposed to generate summaries from documents. However, these approaches seldom simultaneously consider summary diversity, coverage, and balance issues which to a large extent determine the quality of summaries. In this paper, we consider extract-based summarization emphasizing the following three requirements: 1) diversity in summarization, which seeks to reduce redundancy among sentences in the summary; 2) sufficient coverage, which focuses on avoiding the loss of the document's main information when generating the summary; and 3) balance, which demands that different aspects of the document need to have about the same relative importance in the summary. We formulate the extract-based summarization problem as learning a mapping from a set of sentences of a given document to a subset of the sentences that satisfies the above three requirements. The mapping is learned by incorporating several constraints in a structure learning framework, and we explore the graph structure of the output variables and employ structural SVM for solving the resulted optimization problem. Experiments on the DUC2001 data sets demonstrate significant performance improvements in terms of F1 and ROUGE metrics.

More and more structured information in the form of semantic data is nowadays available. It offers a wide range of new possibilities especially for semantic search and Web data integration. However, their effective exploitation still brings about a number of challenges, e.g. usability, scalability and uncertainty. In this paper, we present Dataplorer, a solution designed to address these challenges. We consider the usability through the use of hybrid queries and faceted search, while still preserving the scalability thanks to an extension of inverted index to support this type of query. Moreover, Dataplorer deals with uncertainty by means of a powerful ranking scheme to find relevant results. Our experimental results show that our proposed approach is promising and it makes us believe that it is possible to extend the current IR infrastructure to query and search the Web of data.

Traditional Naive Bayes Classifier performs miserably on web-scale taxonomies. In this paper, we investigate the reasons behind such bad performance. We discover that the low performance are not completely caused by the intrinsic limitations of Naive Bayes, but mainly comes from two largely ignored problems: contradiction pair problem and discriminative evidence cancelation problem. We propose modifications that can alleviate the two problems while preserving the advantages of Naive Bayes. The experimental results show our modified Naive Bayes can significantly improve the performance on real web-scale taxonomies.

Motivated by evolving business requirements and novel enterprise applications, we propose and implement the Semantic Master Data Management (SMDM), a semantics-level enhancement to the existing MDM solutions. The SMDM system publishes relational-based master data as virtual RDF store, and injects instantaneous reasoning capabilities into semantic queries. Two kinds of ontologies are introduced to the system, the core MDM ontology and the external imported domain ontology. SMDM enables data linking among multi-domains, implicit relationship discovery, and declarative definition and extension of business policies and entities. Based on these functions, modern companies can customize their applications and services on demand within the MDM hub. In the demonstration, we build the system environment based on IBM's MDM solution, and run the use cases on the master data of an insurance company.

Traditional personalized search approaches rely solely on individual profiles to construct a user model. They are often confronted by two major problems: data sparseness and cold-start for new individuals. Data sparseness refers to the fact that most users only visit a small portion of Web pages and hence a very sparse user-term relationship matrix is generated, while cold-start for new individuals means that the system cannot conduct any personalization without previous browsing history. Recently, community-based approaches were proposed to use the group's social behaviors as a supplement to personalization. However, these approaches only consider the commonality of a group of users and still cannot satisfy the diverse information needs of different users. In this article, we present a new approach, called collaborative personalized search. It considers not only the commonality factor among users for defining group user profiles and global user profiles, but also the specialties of individuals. Then, a statistical user language model is proposed to integrate the individual model, group user model and global user model together. In this way, the probability that a user will like a Web page is calculated through a two-step smoothing mechanism. First, a global user model is used to smooth the probability of unseen terms in the individual profiles and provide aggregated behavior of global users. Then, in order to precisely describe individual interests by looking at the behaviors of similar users, users are clustered into groups and group-user models are constructed. The group-user models are integrated into an overall model through a cluster-based language model. The behaviors of the group users can be utilized to enhance the performance of personalized search. This model can alleviate the two aforementioned problems and provide a more effective personalized search than previous approaches. Large-scale experimental evaluations are conducted to show that the proposed approach substantially improves the relevance of a search over several competitive methods.

This paper is concerned with the problem of boosting social annotations using propagation, which is also called social propagation. In particular, we focus on propagating social annotations of web pages (e.g., annotations in Del.icio.us). Although social annotations are developing fast, they cover only a small proportion of Web pages on the World Wide Web. To alleviate the low coverage problem, a general propagation model based on Random Surfer is proposed. Specifically, four steps are included: basic propagation, multiple-annotation propagation, multiple-link-type propagation, and constraint-guided propagation. Experimental results show that the proposed model is very effective in increasing coverage of annotations as well as preserving property of social annotations.

The rapidly increasing popularity of community-based Question Answering (cQA) services, e.g. Yahoo! Answers, Baidu Zhidao, etc. have attracted great attention from both academia and industry. Besides the basic problems, like question searching and answer finding, it should be noted that the low participation rate of users in cQA service is the crucial problem which limits its development potential. In this paper, we focus on addressing this problem by recommending answer providers, in which a question is given as a query and a ranked list of users is returned according to the likelihood of answering the question. Based on the intuitive idea for recommendation, we try to introduce topic-level model to improve heuristic term-level methods, which are treated as the baselines. The proposed approach consists of two steps: (1) discovering latent topics in the content of questions and answers as well as latent interests of users to build user profiles; (2) recommending question answerers for new arrival questions based on latent topics and term-level model. Specifically, we develop a general generative model for questions and answers in cQA, which is then altered to obtain a novel computationally tractable Bayesian network model. Experiments are carried out on a real-world data crawled from Yahoo! Answers during Jun 12 2007 to Aug 04 2007, which consists of 118510 questions, 772962 answers and 150324 users. The experimental results reveal significant improvements over the baseline methods and validate the positive influence of topic-level information.

Traditional spectral classification has been proved to be effective in dealing with both labeled and unlabeled data when these data are from the same domain. In many real world applications, however, we wish to make use of the labeled data from one domain (called in-domain) to classify the unlabeled data in a different domain (out-of-domain). This problem often happens when obtaining labeled data in one domain is difficult while there are plenty of labeled data from a related but different domain. In general, this is a transfer learning problem where we wish to classify the unlabeled data through the labeled data even though these data are not from the same domain. In this paper, we formulate this domain-transfer learning problem under a novel spectral classification framework, where the objective function is introduced to seek consistency between the in-domain supervision and the out-of-domain intrinsic structure. Through optimization of the cost function, the label information from the in-domain data is effectively transferred to help classify the unlabeled data from the out-of-domain. We conduct extensive experiments to evaluate our method and show that our algorithm achieves significant improvements on classification performance over many state-of-the-art algorithms.

As a social service in Web 2.0, folksonomy provides the users the ability to save and organize their bookmarks online with "social annotations" or "tags". Social annotations are high quality descriptors of the web pages' topics as well as good indicators of web users' interests. We propose a personalized search framework to utilize folksonomy for personalized search. Specifically, three properties of folksonomy, namely the categorization, keyword, and structure property, are explored. In the framework, the rank of a web page is decided not only by the term matching between the query and the web page's content but also by the topic matching between the user's interests and the web page's topics. In the evaluation, we propose an automatic evaluation framework based on folksonomy data, which is able to help lighten the common high cost in personalized search evaluations. A series of experiments are conducted using two heterogeneous data sets, one crawled from Del.icio.us and the other from Dogear. Extensive experimental results show that our personalized search approach can significantly improve the search quality.

In many Web applications, such as blog classification and new-sgroup classification, labeled data are in short supply. It often happens that obtaining labeled data in a new domain is expensive and time consuming, while there may be plenty of labeled data in a related but different domain. Traditional text classification ap-proaches are not able to cope well with learning across different domains. In this paper, we propose a novel cross-domain text classification algorithm which extends the traditional probabilistic latent semantic analysis (PLSA) algorithm to integrate labeled and unlabeled data, which come from different but related domains, into a unified probabilistic model. We call this new model Topic-bridged PLSA, or TPLSA. By exploiting the common topics between two domains, we transfer knowledge across different domains through a topic-bridge to help the text classification in the target domain. A unique advantage of our method is its ability to maximally mine knowledge that can be transferred between domains, resulting in superior performance when compared to other state-of-the-art text classification approaches. Experimental eval-uation on different kinds of datasets shows that our proposed algorithm can improve the performance of cross-domain text classification significantly.

Most classification algorithms are best at categorizing the Web documents into a few categories, such as the top two levels in the Open Directory Project. Such a classification method does not give very detailed topic-related class information for the user because the first two levels are often too coarse. However, classification on a large-scale hierarchy is known to be intractable for many target categories with cross-link relationships among them. In this paper, we propose a novel deep-classification approach to categorize Web documents into categories in a large-scale taxonomy. The approach consists of two stages: a search stage and a classification stage. In the first stage, a category-search algorithm is used to acquire the category candidates for a given document. Based on the category candidates, we prune the large-scale hierarchy to focus our classification effort on a small subset of the original hierarchy. As a result, the classification model is trained on the small subset before being applied to assign the category for a new document. Since the category candidates are sufficiently close to each other in the hierarchy, a statistical-language-model based classifier using n-gram features is exploited. Furthermore, the structure of the taxonomy can be utilized in this stage to improve the performance of classification. We demonstrate the performance of our proposed algorithms on the Open Directory Project with over 130,000 categories. Experimental results show that our proposed approach can reach 51.8% on the measure of Mi-F1 at the 5th level, which is 77.7% improvement over top-down based SVM classification algorithms.

Designing effective ranking functions is a core problem for information retrieval and Web search since the ranking functions directly impact the relevance of the search results. The problem has been the focus of much of the research at the intersection of Web search and machine learning, and learning ranking functions from preference data in particular has recently attracted much interest. The objective of this paper is to empirically examine several objective functions that can be used for learning ranking functions from preference data. Specifically, we investigate the roles of ties in the learning process. By ties, we mean preference judgments that two documents have equal degree of relevance with respect to a query. This type of data has largely been ignored or not properly modeled in the past. In this paper, we analyze the properties of ties and develop novel learning frameworks which combine ties and preference data using statistical paired comparison models to improve the performance of learned ranking functions. The resulting optimization problems explicitly incorporating ties and preference data are solved using gradient boosting methods. Experimental studies are conducted using three publicly available data sets which demonstrate the effectiveness of the proposed new methods.

With the fast growth of Semantic Web, more and more RDF data and ontologies are created and widely used in Web applications and enterprise information systems. It is reported that the W3C Linking Open Data community project consists of over two billion RDF triples, which are interlinked by about three million RDF links. Recently, efficient RDF data management on top of relational databases gains particular attentions from both Semantic Web community and database community. In this paper, we present effective and efficient Semantic Web data management over DB2, including efficient schema and indexes design for storage, practical ontology reasoning support, and an effective SPARQL-to-SQL translation method for RDF query. Moreover, we show the performance and scalability of our system by an evaluation among well-known RDF stores and discuss future work.

The increasing growth of the World Wide Web constantly enlarges the revenue generated by search engine advertising. Advertisers bid on keywords associated with their products to display their ads on the search result pages. Keyword suggestion methods are proposed to fill the gap between the keywords chosen by advertisers and the popular queries, through finding new relevant keywords according to some statistical information (for example, the keyword co-occurrence). However, there is little effort taking semantic information, such as concept hierarchy, into account. In this paper, we propose a novel keyword suggestion method that fully exploits the semantic knowledge among concept hierarchy. Given a keyword, we first match it with some relevant concepts. Then the relevant concepts are used with their hierarchy to fertilize the meanings of the keywords. Finally new keywords are suggested according to the concept information rather than the statistical co-occurrence of the keyword itself. Experimental results show that our proposed method can successfully provide suggestion that meets the accuracy and coverage requirements

Organizing Web search results into hierarchical categories facilitates users' browsing through Web search results, especially for ambiguous queries where the potential results are mixed together. Previous methods on search result classification are usually based on pre-training a classification model on some fixed and shallow hierarchical categories, where only the top-two-level categories of a Web taxonomy is used. Such classification methods may be too coarse for users to browse, since most search results would be classified into only two or three shallow categories. Instead, a deep hierarchical classifier must provide many more categories. However, the performance of such classifiers is usually limited because their classification effectiveness can deteriorate rapidly at the third or fourth level of a hierarchy. In this paper, we propose a novel algorithm known as Deep Classifier to classify the search results into detailed hierarchical categories with higher effectiveness than previous approaches. Given the search results in response to a query, the algorithm first prunes a wide-ranged hierarchy into a narrow one with the help of some Web directories. Different strategies are proposed to select the training data by utilizing the hierarchical structures. Finally, a discriminative naíve Bayesian classifier is developed to perform efficient and effective classification. As a result, the algorithm can provide more meaningful and specific class labels for search result browsing than shallow style of classification. We conduct experiments to show that the Deep Classifier can achieve significant improvement over state-of-the-art algorithms. In addition, with sufficient off-line preparation, the efficiency of the proposed algorithm is suitable for online application

The paper is concerned with the problem of question recommendation. Specifically, given a question as query, we are to retrieve and rank other questions according to their likelihood of being good recommendations of the queried question. A good recommendation provides alternative aspects around users' interest. We tackle the problem of question recommendation in two steps: first represent questions as graphs of topic terms, and then rank recommendations on the basis of the graphs. We formalize both steps as the tree-cutting problems and then employ the MDL (Minimum Description Length) for selecting the best cuts. Experiments have been conducted with the real questions posted at Yahoo! Answers. The questions are about two domains, 'travel' and 'computers & internet'. Experimental results indicate that the use of the MDL-based tree cut model can significantly outperform the baseline methods of word-based VSM or phrase-based VSM. The results also show that the use of the MDL-based tree cut model is essential to our approach.

As the World Wide Web in China grows rapidly, mining knowledge in Chinese Web pages becomes more and more important. Mining Web information usually relies on the machine learning techniques which require a large amount of labeled data to train credible models. Although the number of Chinese Web pages increases quite fast, it still lacks Chinese labeled data. However, there are relatively sufficient English labeled Web pages. These labeled data, though in different linguistic representations, share a substantial amount of semantic information with Chinese ones, and can be utilized to help classify Chinese Web pages. In this paper, we propose an information bottleneck based approach to address this cross-language classification problem. Our algorithm first translates all the Chinese Web pages to English. Then, all the Web pages, including Chinese and English ones, are encoded through an information bottleneck which can allow only limited information to pass. Therefore, in order to retain as much useful information as possible, the common part between Chinese and English Web pages is inclined to be encoded to the same code (i.e. class label), which makes the cross-language classification accurate. We evaluated our approach using the Web pages collected from Open Directory Project (ODP). The experimental results show that our method significantly improves several existing supervised and semi-supervised classifiers.

This paper is concerned with the problem of mining competitors from the Web automatically. Nowadays the fierce competition in the market necessitates every company not only to know which companies are its primary competitors, but also in which fields the company's rivals compete with itself and what its competitors' strength is in a specific competitive domain. The task of competitor mining that we address in the paper includes mining all the information such as competitors, competing fields and competitors' strength. A novel algorithm called CoMiner is proposed, which tries to conduct a Web-scale mining in a domain-independent manner. The CoMiner algorithm consists of three parts: 1) given an input entity, extracting a set of comparative candidates and then ranking them according to comparability; 2) extracting the fields in which the given entity and its competitors play against each other; 3) identifying and summarizing the competitive evidence that details the competitors' strength. As for evaluation, a prototype system implementing the CoMiner algorithm is presented. An evaluation data set consisting of 70 entities is constructed. 728 competitors and 3,640 competitive fields with 6,381 competitive evidences are discovered with the prototype. The experimental results show that the proposed algorithm is highly effective.

This poster is concerned with the problem of exploring the use of social annotations for improving language models for information retrieval (denoted as LMIR). Two properties of social annotations, namely keyword property and structure property are studied for this aim. The keyword property improves LMIR by concatenating all the annotations of a document to generate a summary of the document. The structure property can boost LMIR further when similarity among annotations and similarity among documents are taken into consideration simultaneously. The two properties of social annotations are leveraged for the use of language modeling with a mixture model named as "Language Annotation Model" (denoted as LAM). Evaluations using del.icio.us data show that LAM outperforms the traditional LMIR approaches significantly.

In many real world applications, labeled data are in short supply. It often happens that obtaining labeled data in a new domain is expensive and time consuming, while there may be plenty of labeled data from a related but different domain. Traditional machine learning is not able to cope well with learning across different domains. In this paper, we address this problem for a text-mining task, where the labeled data are under one distribution in one domain known as in-domain data, while the unlabeled data are under a related but different domain known as out-of-domain data. Our general goal is to learn from the in-domain and apply the learned knowledge to out-of-domain. We propose a co-clustering based classification (CoCC) algorithm to tackle this problem. Co-clustering is used as a bridge to propagate the class structure and knowledge from the in-domain to the out-of-domain. We present theoretical and empirical analysis to show that our algorithm is able to produce high quality classification results, even when the distributions between the two data are different. The experimental results show that our algorithm greatly improves the classification performance over the traditional learning algorithms.

This paper explores the use of social annotations to improve web search. Nowadays, many services, e.g. del.icio.us, have been developed for web users to organize and share their favorite web pages on line by using social annotations. We observe that the social annotations can benefit web search in two aspects: 1) the annotations are usually good summaries of corresponding web pages; 2) the count of annotations indicates the popularity of web pages. Two novel algorithms are proposed to incorporate the above information into page ranking: 1) SocialSimRank (SSR) calculates the similarity between social annotations and web queries; 2) SocialPageRank (SPR) captures the popularity of web pages. Preliminary experimental results show that SSR can find the latent semantic association between queries and annotations, while SPR successfully measures the quality (popularity) of a web page from the web users ’ perspective. We further evaluate the proposed methods empirically with 50 manually constructed queries and 3000 auto-generated queries on a dataset crawled from del.icio.us. Experiments show that both SSR and SPR benefit web search significantly.

The emergence of personalized homepage services, e.g. personalized Google Homepage and Microsoft Windows Live, has enabled Web users to select Web contents of interest and to aggregate them in a single Web page. The web contents are often predefined content blocks provided by the service providers. However, it involves intensive manual efforts to define the content blocks and maintain the information in it. In this paper, we propose a novel personalized homepage system, called .Homepage Live., to allow end users to use drag-and-drop actions to collect their favorite Web content blocks from existing Web pages and organize them in a single page. Moreover, Homepage Live automatically traces the changes of blocks with the evolvement of the container pages by measuring the tree edit distance of the selected blocks. By exploiting the immutable elements of Web pages, the tracing algorithm performance is significantly improved. The experimental results demonstrate the effectiveness and efficiency of our algorithm.

This paper is concerned with the problem of browsing social annotations. Today, a lot of services (e.g., Del.icio.us, Filckr) have been provided for helping users to manage and share their favorite URLs and photos based on social annotations. Due to the exponential increasing of the social annotations, more and more users, however, are facing the problem how to effectively find desired resources from large annotation data. Existing methods such as tag cloud and annotation matching work well only on small annotation sets. Thus, an effective approach for browsing large scale annotation sets and the associated resources is in great demand by both ordinary users and service providers. In this paper, we propose a novel algorithm, namely Effective Large Scale Annotation Browser (ELSABer), to browse large-scale social annotation data. ELSABer helps the users browse huge number of annotations in a semantic, hierarchical and efficient way. More specifically, ELSABer has the following features: 1) the semantic relations between annotations are explored for browsing of similar resources; 2) the hierarchical relations between annotations are constructed for browsing in a top-down fashion; 3) the distribution of social annotations is studied for efficient browsing. By incorporating the personal and time information, ELSABer can be further extended for personalized and time-related browsing. A prototype system is implemented and shows promising results.

Weblogs have become a prevalent source of information for people to express themselves. In general, there are two genres of contents in weblogs. The first kind is about the webloggers' personal feelings, thoughts or emotions. We call this kind of weblogs affective articles. The second kind of weblogs is about technologies and different kinds of informative news. In this paper, we present a machine learning method for classifying informative and affective articles among weblogs. We consider this problem as a binary classification problem. By using machine learning approaches, we achieve about 92% on information retrieval performance measures including precision, recall and F1. We set up three studies on the applications of above classification approach in both research and industrial fields. The above classification approach is used to improve the performance of classification of emotions from weblog articles. We also develop an intent-driven weblog-search engine based on the classification techniques to improve the satisfaction of Web users. Finally, our approach is applied to search for weblogs with a great deal of informative articles.

It is widely believed that some queries submitted to search engines are by nature ambiguous (e.g., java, apple). However, few studies have investigated the questions of "how many queries are ambiguous?" and "how can we automatically identify an ambiguous query?" This paper deals with these issues. First, we construct the taxonomy of query ambiguity, and ask human annotators to manually classify queries based upon it. From manually labeled results, we find that query ambiguity is to some extent predictable. We then use a supervised learning approach to automatically classify queries as being ambiguous or not. Experimental results show that we can correctly identify 87% of labeled queries. Finally, we estimate that about 16% of queries in a real search log are ambiguous.

This paper studies the problem of discovering latent associations among objects in text documents. Specifically, given two sets of objects and various types of co-occurrence data concerning the objects existing in texts, we aim to discover the hidden or latent associative relationships between the two sets of objects. Existing methods are not directly applicable as they are unable to consider all this information. For example, the probabilistic mixture model called Separable Mixture Model (SMM) proposed by Hofmann can use only one type of co-occurrences to mine latent associations. This paper proposes a more general probabilistic mixture model called the Typed Separable Mixture Model (TSMM), which is able to use all types of co-occurrences within a single framework. Experimental results based on the expert/expertise mining task show that TSMM outperforms SMM significantly.

This paper attempts to accomplish a novel task of mining competitive information with respect to an entity (such as a company, product, person) from the web. An algorithm called "CoMiner" is proposed, which first extracts a set of comparative candidates of the input entity and then ranks them according to the comparability, and finally extracts the competitive fields. The experimental results show that the proposed algorithm drafts a complete picture of competitive relation of a given entity effectively.

Chinese Weblogs have been expanded in an incredible speed in recent years. There is plentiful personal information in Weblogs. In this paper, we propose a text classification based approach to automatically identify the interests of a Weblogger. To solve the problems arising out of class Weblog documents, the technique of heterogeneous classifiers combination is used. We also use hierarchical classification technique to identify much specific interests. Experiments show that our interest identification approach has a high accuracy and, for most Webloggers in our experiments, their interests implied in the contents of blogs could be well identified by using this approach

In order to obtain a machine understandable semantics for web resources, research on the Semantic Web tries to annotate web resources with concepts and relations from explicitly defined formal ontologies. This kind of formal annotation is usually done manually or semi-automatically. In this paper, we explore a complement approach that focuses on the "social annotations of the web" which are annotations manually made by normal web users without a pre-defined formal ontology. Compared to the formal annotations, although social annotations are coarse-grained, informal and vague, they are also more accessible to more people and better reflect the web resources' meaning from the users' point of views during their actual usage of the web resources. Using a social bookmark service as an example, we show how emergent semantics [2] can be statistically derived from the social annotations. Furthermore, we apply the derived emergent semantics to discover and search shared web bookmarks. The initial evaluation on our implementation shows that our method can effectively discover semantically related web bookmarks that current social bookmark service can not discover easily.

Feature selection has been widely applied in text categorization and clustering. Compared to unsupervised selection, supervised feature selection is more successful in filtering out noise in most cases. However, due to a lack of label information, clustering can hardly exploit supervised selection. Some studies have proposed to solve this problem by "pseudoclass." As empirical results show, this method is sensitive to selection criteria and data sets. In this paper, we propose a novel feature coselection for Web document clustering, which is called multitype features coselection for clustering (MFCC). MFCC uses intermediate clustering results in one type of feature space to help the selection in other types of feature spaces. Our experiments show that for most selection criteria, MFCC reduces effectively the noise introduced by "pseudoclass," and further improves clustering performance.

Memory-based approaches for collaborative filtering identify the similarity between two users by comparing their ratings on a set of items. In the past, the memory-based approach has been shown to suffer from two fundamental problems: data sparsity and difficulty in scalability. Alternatively, the model-based approach has been proposed to alleviate these problems, but this approach tends to limit the range of users. In this paper, we present a novel approach that combines the advantages of these two approaches by introducing a smoothing-based method. In our approach, clusters generated from the training data provide the basis for data smoothing and neighborhood selection. As a result, we provide higher accuracy as well as increased efficiency in recommendations. Empirical studies on two datasets (EachMovie and MovieLens) show that our new proposed approach consistently outperforms other state-of-art collaborative filtering algorithms.

Link analysis algorithms have been extensively used in Web information retrieval. However, current link analysis algorithms generally work on a flat link graph, ignoring the hierarchal structure of the Web graph. They often suffer from two problems: the sparsity of link graph and biased ranking of newly-emerging pages. In this paper, we propose a novel ranking algorithm called Hierarchical Rank as a solution to these two problems, which considers both the hierarchical structure and the link structure of the Web. In this algorithm, Web pages are first aggregated based on their hierarchical structure at directory, host or domain level and link analysis is performed on the aggregated graph. Then, the importance of each node on the aggregated graph is distributed to individual pages belong to the node based on the hierarchical structure. This algorithm allows the importance of linked Web pages to be distributed in the Web page space even when the space is sparse and contains new pages. Experimental results on the .GOV collection of TREC 2003 and 2004 show that hierarchical ranking algorithm consistently outperforms other well-known ranking algorithms, including the PageRank, BlockRank and LayerRank. In addition, experimental results show that link aggregation at the host level is much better than link aggregation at either the domain or directory levels.

Semantic Portal is the next generation of web portals that are powered by Semantic Web technologies for improved information sharing and exchange for a community of users. Current methods of searching in Semantic Portals are limited to keyword-based search using information retrieval (IR) techniques, ontology-based formal query and reasoning, or a simple combination of the two. In this paper, we propose an enhanced model that tightly integrates IR with formal query and reasoning to fully utilize both textual and semantic information for searching in Semantic Portals. The model extends the search capabilities of existing methods and can answer more complex search requests. The ideas in a fuzzy description logic (DL) IR model and a formal DL query method are employed and combined in our model. Based on the model, a semantic search service is implemented and evaluated. The evaluation shows very large improvements over existing methods.

The performance of web search engines may often deteriorate due to the diversity and noisy information contained within web pages. User click-through data can be used to introduce more accurate description (metadata) for web pages, and to improve the search performance. However, noise and incompleteness, sparseness, and the volatility of web pages and are three major challenges for research work on user click-through log mining. In this paper, we propose a novel iterative reinforced algorithm to utilize the user click-through data to improve search performance. The algorithm fully explores the interrelations between and web pages, and effectively finds virtual queries for web pages and overcomes the challenges discussed above. Experiment results on a large set of MSN click-through log data show a significant improvement on search performance over the naive query log mining algorithm as well as the baseline search engine.

We introduce the Multiple Relationship Similarity Spreading Algorithm (MRSSA) to enhance IR effectiveness. This method has similarity computed in an iterative "spreading" fashion for multiple object types, combining both inter- and intra-object relationships. We demonstrate the value of this approach in the context of the WWW, where the key objects are web pages and queries, Relationships considered are derived from hyperlinks (in- and out-links) and click-through logs.

Most existing categorization algorithms deal with homogeneous Web data objects, and consider interrelated objects as additional features when taking the interrelationships with other types of objects into account. However, focusing on any single aspects of these interrelationships and objects does not fully reveal their true categories. In this paper, we propose a categorization algorithm, the iterative reinforcement categorization algorithm (IRC), to exploit the full interrelationships between the heterogeneous objects on the Web. IRC attempts to classify the interrelated Web objects by iterative reinforcement between individual classification results of different types via the interrelationships. Experiments on a clickthrough log dataset from MSN search engine show that, with the Fl measures, IRC achieves a 26.4% improvement over a pure content-based classification method, a 21% improvement over a query metadata-based method, and a 16.4% improvement over a virtual document-based method. Furthermore, our experiments show that IRC converges rapidly.

Content analysis and citation analysis are two common methods in recommending system. Compared with content analysis, citation analysis can discover more implicitly related papers. However, the citation-based methods may introduce more noise in citation graph and cause topic drift. Some work combine content with citation to improve similarity measurement. The problem is that the two features are not used to reinforce each other to get better result. To solve the problem, we propose a new algorithm, Topic Sensitive Similarity Propagation (TSSP), to effectively integrate content similarity into similarity propagation. TSSP has two parts: citation context based propagation and iterative reinforcement. First, citation contexts provide clues for which papers are topic related to and filter out less irrelevant citations. Second, iteratively integrating content and citation similarity enable them to reinforce each other during the propagation. The experimental results of a user study show TSSP outperforms other algorithms in almost all cases.