Affiliate marketing, a component of modern digital marketing, leverages partnerships among merchants, promoters, and consumers to enhance item visibility and drive sales. Promoters act as critical intermediaries, sharing items with their communities to promote items while earning commissions. Accurate prediction of the sharing rate of promoters enables platforms to optimize recommendation performance, thereby improving promotional efficiency. However, existing related methods are mainly designed for consumer-oriented scenarios (C-end), and face significant limitations in modeling the promoters (B-end), which are typically characterized by audience group attachment. Specifically, three core challenges emerge: (1) how to organically integrate audience preferences while maintaining promoter dominance, (2) how to accommodate promoters' diverse interest scopes, and (3) how to capture the complex one-to-many relationships between promoters and their audiences. For Challenge (1), we employ a dynamic routing mechanism based on interest capsules to model the diverse interests of promoters, where audience groups are used to optimize the interest routing via a novel dual-channel attention mechanism, thus allowing audience groups to explicitly participate in the promoter decision-making process with an auxiliary role. For Challenge (2), a parameter-free, confidence-aware interest activation mechanism is introduced to adaptively select sparse interest capsules. For Challenge (3), we pioneer the use of hypergraphs in CTR prediction to model one-to-many relationships between promoters and audiences. Extensive experiments are conducted on two real-world datasets to validate the effectiveness of our approach. Furthermore, the model is deployed on the Alimama platform, which hosts over 100,000 promoters. Online A/B testing results demonstrate that our method achieves a 5.31% average improvement over online baselines.

In recent years, affiliate marketing has emerged as a revenue-sharing strategy where merchants collaborate with promoters to promote their products. It not only increases product exposure but also allows promoters to earn a commission. This paper addresses the pivotal yet under-explored challenge in affiliate marketing: accurately assessing and predicting the contributions of promoters in product promotion. We design a novel metric for evaluating the indirect contributions of the promoter, called propagation scale. Unfortunately, existing time series forecasting techniques fail to deliver accurate predictions due to the propagation scale being influenced by multiple factors and the inherent complexities arising from dynamic scenarios. To address this issue, we decouple the network structure from the node signals and propose a two-stage solution: initially, the basic self-sales and network structure prediction are conducted separately, followed by the synthesis of the propagation scale. Specifically, we design a graph convolution encoding scheme based on descendant neighbors and incorporate hypergraph convolution to efficiently capture complex promotional dynamics. Additionally, three auxiliary tasks are employed: self-sales prediction for base estimations, descendant prediction to synthesize propagation scale, and promoter activation prediction to mitigate high volatility issues. Extensive offline experiments on large-scale industrial datasets validate the superiority of our method. We further deploy our model on Alimama platform with over 100,000 promoters, achieving a 9.29% improvement in GMV and a 5.89% increase in sales volume.

Although multi-task learning (MTL) has been a preferred approach and successfully applied in many real-world scenarios, MTL models are not guaranteed to outperform single-task models on all tasks mainly due to the negative effects of conflicting gradients among the tasks. In this paper, we fully examine the influence of conflicting gradients and further emphasize the importance and advantages of achieving non-conflicting gradients which allows simple but effective trade-off strategies among the tasks with stable performance. Based on our findings, we propose the Gradient Deconfliction via Orthogonal Projections onto Subspaces (GradOPS) spanned by other task-specific gradients. Our method not only solves all conflicts among the tasks, but can also effectively search for diverse solutions towards different trade-off preferences among the tasks. Theoretical analysis on convergence is provided, and performance of our algorithm is fully testified on multiple benchmarks in various domains. Results demonstrate that our method can effectively find multiple state-of-the-art solutions with different trade-off strategies among the tasks on multiple datasets.

In the world of E-Commerce, the core task is to understand the personalized preference from various kinds of heterogeneous information, such as textual reviews, item images and historical behaviors. In current systems, these heterogeneous information are mainly exploited to generate better item or user representations. For example, in scenario of visual search, the importance of modeling query image has been widely acknowledged. But, these existing solutions focus on improving the representation quality of the query image, overlooking the personalized visual preference of the user. Note that the visual features affect the user's decision significantly, e.g., the user could be more likely to click the items with her preferred design. Hence, it is fruitful to exploit the visual preference to deliver better capacity for personalization.

Mobile Taobao Application delivers search services on multiple scenarios that take textual, visual, or product queries. This paper aims to propose a unified graph neural network for these search scenarios to leverage data from multiple scenarios and jointly optimize search performances with less training and maintenance costs. Towards this end, this paper proposes BOMGraph, BOosting Multi-scenario E-commerce Search with a unified Graph neural network. BOMGraph is embodied with several components to address challenges in multi-scenario search. It captures heterogeneous information flow across scenarios by inter-scenario and intra-scenario metapaths. It learns robust item representations by disentangling specific characteristics for different scenarios and encoding common knowledge across scenarios. It alleviates label scarcity and long-tail problems in scenarios with low traffic by contrastive learning with cross-scenario augmentation. BOMGraph has been deployed in production by Alibaba's E-commerce search advertising platform. Both offline evaluations and online A/B tests demonstrate the effectiveness of BOMGraph.

Despite the development of ranking optimization techniques, pointwise loss remains the dominating approach for click-through rate prediction. It can be attributed to the calibration ability of the pointwise loss since the prediction can be viewed as the click probability. In practice, a CTR prediction model is also commonly assessed with the ranking ability. To optimize the ranking ability, ranking loss (e.g., pairwise or listwise loss) can be adopted as they usually achieve better rankings than pointwise loss. Previous studies have experimented with a direct combination of the two losses to obtain the benefit from both losses and observed an improved performance. However, previous studies break the meaning of output logit as the click-through rate, which may lead to sub-optimal solutions. To address this issue, we propose an approach that can Jointly optimize the Ranking and Calibration abilities (JRC for short). JRC improves the ranking ability by contrasting the logit value for the sample with different labels and constrains the predicted probability to be a function of the logit subtraction. We further show that JRC consolidates the interpretation of logits, where the logits model the joint distribution. With such an interpretation, we prove that JRC approximately optimizes the contextualized hybrid discriminative-generative objective. Experiments on public and industrial datasets and online A/B testing show that our approach improves both ranking and calibration abilities. Since May 2022, JRC has been deployed on the display advertising platform of Alibaba and has obtained significant performance improvements.

Recently, many E-commerce search models are based on Graph Neural Networks (GNNs). Despite their promising performances, they are (1) lacking proper semantic representation of product contents; (2) less efficient for industry-scale graphs; and (3) less accurate on long-tail queries and cold-start products. To address these problems simultaneously, this paper proposes CC-GNN, a novel Content Collaborative Graph Neural Network. Firstly, CC-GNN enables content phrases to participate explicitly in graph propagation to capture the proper meaning of phrases and semantic drifts. Secondly, CC-GNN presents several efforts towards a more scalable graph learning framework, including efficient graph construction, MetaPath-guided Message Passing, and Difficulty-aware Representation Perturbation for graph contrastive learning. Furthermore, CC-GNN adopts Counterfactual Data Supplement at both supervised and contrastive learning to resolve the long-tail/cold-start problems. Extensive experiments on a real E-commerce dataset of 100-million-scale nodes show that CC-GNN produces significant improvements over existing methods (i.e., more than 10% improvements in terms of several key evaluation metrics for overall, long-tail queries and cold-start products) while reducing computational complexity. The proposed components of CC-GNN can be applied to other models for search and recommendation tasks. Experiments on a public dataset show that applying the proposed components can improve the performance of different recommendation models.

Recently, Multi-Scenario Learning (MSL) is widely used in recommendation and retrieval systems in the industry because it facilitates transfer learning from different scenarios, mitigating data sparsity and reducing maintenance cost. These efforts produce different MSL paradigms by searching more optimal network structure, such as Auxiliary Network, Expert Network, and Multi-Tower Network. It is intuitive that different scenarios could hold their specific characteristics, activating the user's intents quite differently. In other words, different kinds of auxiliary features would bear varying importance under different scenarios. With more discriminative feature representations refined in a scenario-aware manner, better ranking performance could be easily obtained without expensive search for the optimal network structure. Unfortunately, this simple idea is mainly overlooked but much desired in real-world systems.

Model-based methods for recommender systems have been studied extensively for years. Modern recommender systems usually resort to 1) representation learning models which define user-item preference as the distance between their embedding representations, and 2) embedding-based Approximate Nearest Neighbor (ANN) search to tackle the efficiency problem introduced by large-scale corpus. While providing efficient retrieval, the embedding-based retrieval pattern also limits the model capacity since the form of user-item preference measure is restricted to the distance between their embedding representations. However, for other more precise user-item preference measures, e.g., preference scores directly derived from a deep neural network, they are computationally intractable because of the lack of an efficient retrieval method, and an exhaustive search for all user-item pairs is impractical.

We study the search traffic forecasting problem for guaranteed search advertising (GSA) application in e-commerce platforms. The consumers express their purchase intents by posing queries to the e-commerce search engine. GSA is a type of guaranteed delivery (GD) advertising strategy, which forecasts the traffic of search queries, and charges the advertisers according to the predicted volumes of search queries the advertisers willing to buy. We employ the time series forecasting method to make the search traffic prediction. Different from existing time series prediction methods, search queries are semantically meaningful, with semantically similar queries possessing similar time series. And they can be grouped according to the brands or categories they belong to, exhibiting hierarchical structures. To fully take advantage of these characteristics, we design a SemanTic AwaRe Deep hierarchical fOrecasting Model (STARDOM for short) which explores the queries' semantic information and the hierarchical structures formed by the queries. Specifically, to exploit hierarchical structure, we propose a reconciliation learning module. It leverages deep learning model to learn the reconciliation relation between the hierarchical series in the latent space automatically, and forces the coherence constraints through a distill reconciliation loss. To exploit semantic information, we propose a semantic representation module and generate semantic aware series embeddings for queries. Extensive experiments are conducted to confirm the effectiveness of the proposed method.

Extracting expressive visual features is crucial for accurate Click-Through-Rate (CTR) prediction in visual search advertising systems. Current commercial systems use off-the-shelf visual encoders to facilitate fast online service. However, the extracted visual features are coarse-grained and/or biased. In this paper, we present a visual encoding framework for CTR prediction to overcome these problems. The framework is based on contrastive learning which pulls positive pairs closer and pushes negative pairs apart in the visual feature space. To obtain fine-grained visual features, we present contrastive learning supervised by click-through data to fine-tune the visual encoder. To reduce sample selection bias, firstly we train the visual encoder offline by leveraging both unbiased self-supervision and click supervision signals. Secondly, we incorporate a debiasing network in the online CTR predictor to adjust the visual features by contrasting high impression items with selected, low impression items. We deploy the framework in a mobile E-commerce app. Offline experiments on billion-scale datasets and online experiments demonstrate that the proposed framework can make accurate and unbiased predictions.

Product searching is fundamental in online e-commerce systems, it needs to quickly and accurately find the products that users required. Relevance is essential for e-commerce search, which role is avoiding displaying products that do not match search intent and optimizing user experience. Measuring semantic relevance is necessary because distributional biases between search queries and product titles may lead to large lexical differences between relevant textual expressions. Several problems limit the performance of semantic relevance learning, including extremely long-tail product distribution and low-quality labeled data. Recent works attempt to conduct relevance learning through user behaviors. However, noisy user behavior can easily cause inadequately semantic modeling. Therefore, it is valuable but challenging to utilize user behavior in relevance learning. In this paper, we first propose a weakly supervised contrastive learning framework that focuses on how to provide effective semantic supervision and generate reasonable representation. We utilize topology structure information contained in a user behavior heterogeneous graph to design a semantically aware data construction strategy. Besides, we propose a contrastive learning framework suitable for e-commerce scenarios with targeted improvements in data augmentation and training objectives. For relevance calculation, we propose a novel hybrid method that combines fine-tuning and transfer learning. It eliminates the negative impacts caused by distributional bias and guarantees semantic matching capabilities. Extensive experiments and analyses show the promising performance of proposed methods in relevance learning.

An industrial recommender system generally presents a hybrid list that contains results from multiple subsystems. In practice, each subsystem is optimized with its own feedback data to avoid the disturbance among different subsystems. However, we argue that such data usage may lead to sub-optimal online performance because of thedata sparsity. To alleviate this issue, we propose to extract knowledge from thesuper-domain that contains web-scale and long-time impression data, and further assist the online recommendation task (downstream task). To this end, we propose a novel industrial KnowlEdge Extraction and Plugging (KEEP) framework, which is a two-stage framework that consists of 1) a supervised pre-training knowledge extraction module on super-domain, and 2) a plug-in network that incorporates the extracted knowledge into the downstream model. This makes it friendly for incremental training of online recommendation. Moreover, we design an efficient empirical approach for KEEP and introduce our hands-on experience during the implementation of KEEP in a large-scale industrial system. Experiments conducted on two real-world datasets demonstrate that KEEP can achieve promising results. It is notable that KEEP has also been deployed on the display advertising system in Alibaba, bringing a lift of +5.4% CTR and +4.7% RPM.

Deep learning techniques have been applied widely in industrial recommendation systems. However, far less attention has been paid on the overfitting problem of models in recommendation systems, which, on the contrary, is recognized as a critical issue for deep neural networks. In the context of Click-Through Rate (CTR) prediction, we observe an interesting one-epoch overfitting problem: the model performance exhibits a dramatic degradation at the beginning of the second epoch. Such a phenomenon has been witnessed widely in real-world applications of CTR models. Thereby, the best performance is usually achieved by training with only one epoch. To understand the underlying factors behind the one-epoch phenomenon, we conduct extensive experiments on the production data set collected from the display advertising system of Alibaba. The results show that the model structure, the optimization algorithm with a fast convergence rate, and the feature sparsity are closely related to the one-epoch phenomenon. We also provide a likely hypothesis for explaining such a phenomenon and conduct a set of proof-of-concept experiments. We hope this work can shed light on the future research on training more epochs for better performance.

Click-Through Rate (CTR) prediction, estimating the probability of a user clicking on items, plays a key fundamental role in sponsored search. E-commerce platforms display organic search results and advertisements (ads), collectively called items, together as a mixed list. The items displayed around the predicted ad, i.e. external items, may affect the user clicking on the predicted. Previous CTR models assume the user click only relies on the ad itself, which overlooks the effects of external items, referred to as external effects, or externalities. During the advertising prediction, the organic results have been generated by the organic system, while the final displayed ads on multiple ad slots have not been figured out, which leads to two challenges: 1) the predicted (target) ad may win any ad slot, bringing about diverse externalities. 2) external ads are undetermined, resulting in incomplete externalities. Facing the above challenges, inspired by the Transformer, we propose EXternality TRansformer (EXTR) which regards target ad with all slots as query and external items as key&value to model externalities in all exposure situations in parallel. Furthermore, we design a Potential Allocation Generator (PAG) for EXTR, to learn the allocation of potential external ads to complete the externalities. Extensive experimental results on Alibaba datasets demonstrate the effectiveness of externalities in the task of CTR prediction and illustrate that our proposed approach can bring significant profits to the real-world e-commerce platform. EXTR now has been successfully deployed in the online search advertising system in Alibaba, serving the main traffic.

The importance of modeling contextual information within a search session has been widely acknowledged. However, learning representations of multi-query multi-modal (MM) search, in which Mobile Taobao users repeatedly submit textual and visual queries, remains unexplored in literature. Previous work which learns task-specific representations of textual query sessions fails to capture diverse query types and correlations in MM search sessions. This paper presents to represent MM search sessions by heterogeneous graph neural network (HGN). A multi-view contrastive learning framework is proposed to pretrain the HGN, with two views to model different intra-query, inter-query, and inter-modality information diffusion in MM search. Extensive experiments demonstrate that, the pretrained session representation can benefit state-of-the-art baselines on various downstream tasks, such as personalized click prediction, query suggestion, and intent classification.

Exploration-Exploitation (E& E) algorithms are commonly adopted to deal with the feedback-loop issue in large-scale online recommender systems. Most of existing studies believe that high uncertainty can be a good indicator of potential reward, and thus primarily focus on the estimation of model uncertainty. We argue that such an approach overlooks the subsequent effect of exploration on model training. From the perspective of online learning, the adoption of an exploration strategy would also affect the collecting of training data, which further influences model learning. To understand the interaction between exploration and training, we design a Pseudo-Exploration module that simulates the model updating process after a certain item is explored and the corresponding feedback is received. We further show that such a process is equivalent to adding an adversarial perturbation to the model input, and thereby name our proposed approach as an the Adversarial Gradient Driven Exploration (AGE). For production deployment, we propose a dynamic gating unit to pre-determine the utility of an exploration. This enables us to utilize the limited amount of resources for exploration, and avoid wasting pageview resources on ineffective exploration. The effectiveness of AGE was firstly examined through an extensive number of ablation studies on an academic dataset. Meanwhile, AGE has also been deployed to one of the world-leading display advertising platforms, and we observe significant improvements on various top-line evaluation metrics.

In e-commerce, ad creatives play an important role in effectively delivering product information to users. The purpose of online creative selection is to learn users' preferences for ad creatives, and to select the most appealing design for users to maximize Click-Through Rate (CTR). However, the existing common practices in the industry usually place the creative selection after the ad ranking stage, and thus the optimal creative fails to reflect the influence on the ad ranking stage. To address these issues, we propose a novel Cascade Architecture of Creative Selection (CACS), which is built before the ranking stage to joint optimization of intra-ad creative selection and inter-ad ranking. To improve the efficiency, we design a classic two-tower structure and allow creative embeddings of the creative selection stage to share with the ranking stage. To boost the effectiveness, on the one hand, we propose a soft label list-wise ranking distillation method to distill the ranking knowledge from the ranking stage to guide CACS learning; and on the other hand, we also design an adaptive dropout network to encourage the model to probabilistically ignore ID features in favor of content features to learn multi-modal representations of the creative. Most of all, the ranking model obtains the optimal creative information of each ad from our CACS, and uses all available features to improve the performance of the ranking model. We have launched our solution in Taobao advertising platform and have obtained significant improvements both in offline and online evaluations.

Feature interaction has been recognized as an important problem in machine learning, which is also very essential for click-through rate (CTR) prediction tasks. In recent years, Deep Neural Networks (DNNs) can automatically learn implicit nonlinear interactions from original sparse features, and therefore have been widely used in industrial CTR prediction tasks. However, the implicit feature interactions learned in DNNs cannot fully retain the complete representation capacity of the original and empirical feature interactions (e.g., cartesian product) without loss. For example, a simple attempt to learn the combination of feature A and feature B < A, B > as the explicit cartesian product representation of new features can outperform previous implicit feature interaction models including factorization machine (FM)-based models and their variations. This indicates there is still a big gap between explicit and implicit feature interaction models. However, to learn all the explicit feature interaction (cartesian product) representations requires a very large sample size along with N times of original parameter space (where N is quite large in most industrial applications). In this paper, we propose a Co-Action Network (CAN) to approximate the explicit pairwise feature interactions without introducing too many additional parameters. More specifically, giving feature A and its associated feature B, their feature interaction is modeled by learning two sets of parameters: 1) the embedding of feature A, and 2) a Multi-Layer Perceptron (MLP) to represent feature B. The approximated feature interaction can be obtained by passing the embedding of feature A through the MLP network of feature B. We refer to such pairwise feature interaction as feature co-action, and such a Co-Action Network unit can provide a very powerful capacity to fitting complex feature interactions. In addition, FM can be viewed as a special case of the CAN unit when the MLP is a single layer with only one output. Experimental results on public and industrial datasets show that CAN outperforms state-of-the-art CTR models and the cartesian product method. Moreover, CAN has been deployed in the display advertisement system in Alibaba, obtaining 12% improvement on CTR and 8% on Revenue Per Mille (RPM), which is a great improvement to the business. The code for experiments in this paper is open-sourced\footnotehttps://github.com/CAN-Paper/Co-Action-Network.

User-User interaction recommendation, or interaction recommendation, is an indispensable service in social platforms, where the system automatically predicts with whom a user wants to interact. In real-world social platforms, we observe that user interactions may occur in diverse scenarios, and new scenarios constantly emerge, such as new games or sales promotions. There are two challenges in these emerging scenarios: (1) The behavior of users on the emerging scenarios could be different from existing ones due to the diversity among scenarios; (2) Emerging scenarios may only have scarce user behavioral data for model learning. Towards these two challenges, we present KoMen, a Domain Knowledge Guided Meta-learning framework for Interaction Recommendation. KoMen first learns a set of global model parameters shared among all scenarios and then quickly adapts the parameters for an emerging scenario based on its similarities with the existing ones. There are two highlights of KoMen: (1) KoMen customizes global model parameters by incorporating domain knowledge of the scenarios (e.g., a taxonomy that organizes scenarios by their purposes and functions), which captures scenario inter-dependencies with very limited training. (2) KoMen learns the scenario-specific parameters through a mixture-of-expert architecture, which reduces model variance resulting from data scarcity while still achieving the expressiveness to handle diverse scenarios. Extensive experiments demonstrate that KoMen achieves state-of-the-art performance on a public benchmark dataset and a large-scale real industry dataset. Remarkably, KoMen improves over the best baseline w.r.t. weighted ROC-AUC by 2.14% and 2.03% on the two datasets, respectively. Our code is available at: https://github.com/Veronicium/koMen.

As recommendation is essentially a comparative (or ranking) process, a good explanation should illustrate to users why an item is believed to be better than another, i.e., comparative explanations about the recommended items. Ideally, after reading the explanations, a user should reach the same ranking of items as the system’s. Unfortunately, little research attention has yet been paid on such comparative explanations.

In this article, we propose a Latent Dirichlet Allocation– (LDA) based topic-graph probabilistic personalization model for Web search. This model represents a user graph in a latent topic graph and simultaneously estimates the probabilities that the user is interested in the topics, as well as the probabilities that the user is not interested in the topics. For a given query issued by the user, the webpages that have higher relevancy to the interested topics are promoted, and the webpages more relevant to the non-interesting topics are penalized. In particular, we simulate a user’s search intent by building two profiles: A positive user profile for the probabilities of the user is interested in the topics and a corresponding negative user profile for the probabilities of being not interested in the the topics. The profiles are estimated based on the user’s search logs. A clicked webpage is assumed to include interesting topics. A skipped (viewed but not clicked) webpage is assumed to cover some non-interesting topics to the user. Such estimations are performed in the latent topic space generated by LDA. Moreover, a new approach is proposed to estimate the correlation between a given query and the user’s search history so as to determine how much personalization should be considered for the query. We compare our proposed models with several strong baselines including state-of-the-art personalization approaches. Experiments conducted on a large-scale real user search log collection illustrate the effectiveness of the proposed models.

Traditional industry recommendation systems usually use data in a single domain to train models and then serve the domain. However, a large-scale commercial platform often contains multiple domains, and its recommendation system often needs to make click-through rate (CTR) predictions for multiple domains. Generally, different domains may share some common user groups and items, and each domain may have its own unique user groups and items. Moreover, even the same user may have different behaviors in different domains. In order to leverage all the data from different domains, a single model can be trained to serve all domains. However, it is difficult for a single model to capture the characteristics of various domains and serve all domains well. On the other hand, training an individual model for each domain separately does not fully use the data from all domains. In this paper, we propose the Star Topology Adaptive Recommender (STAR) model to train a single model to serve all domains by leveraging data from all domains simultaneously, capturing the characteristics of each domain, and modeling the commonalities between different domains. Essentially, the net- work of each domain consists of two factorized networks: one centered network shared by all domains and the domain-specific network tailored for each domain. For each domain, we combine these two factorized networks and generate a unified network by element-wise multiplying the weights of the shared network and those of the domain-specific network, although these two factorized networks can be combined using other functions, which is open for further research. Most importantly, STAR can learn the shared network from all the data and adapt domain-specific parameters according to the characteristics of each domain. The experimental results from production data validate the superiority of the proposed STAR model. Since late 2020, STAR has been deployed in the display advertising system of Alibaba, obtaining 8.0% improvement on CTR and 6.0% increase on RPM (Revenue Per Mille).

The large-scale recommender system mainly consists of two stages: matching and ranking. The matching stage (also known as the retrieval step) identifies a small fraction of relevant items from billion-scale item corpus in low latency and computational cost. Item-to-item collaborative filtering (item-based CF) and embedding-based retrieval (EBR) have been long used in the industrial matching stage owing to its efficiency. However, item-based CF is hard to meet personalization, while EBR has difficulty in satisfying diversity. In this paper, we propose a novel matching architecture, Path-based Deep Network (named PDN), through incorporating both personalization and diversity to enhance matching performance. Specifically, PDN is comprised of two modules: Trigger Net and Similarity Net. PDN utilizes Trigger Net to capture the user's interest in each of his/her interacted item. Similarity Net is devised to evaluate the similarity between each interacted item and the target item based on these items' profile and CF information. The final relevance between the user and the target item is calculated by explicitly considering user's diverse interests, \ie aggregating the relevance weights of the related two-hop paths (one hop of a path corresponds to user-item interaction and the other to item-item relevance). Furthermore, we describe the architecture design of the proposed PDN in a leading real-world E-Commerce service (Mobile Taobao App). Based on offline evaluations and online A/B test, we show that PDN outperforms the existing solutions for the same task. The online results also demonstrate that PDN can retrieve more personalized and more diverse items to significantly improve user engagement. Currently, PDN system has been successfully deployed at Mobile Taobao App and handling major online traffic.

Sharing recommendation is becoming ubiquitous at almost every e-commerce website, where a user will be recommended a list of users when he wants to share something with others. With the tremendous growth of online shopping users, sharing recommendation confronts several distinct difficulties: 1) how to establish a unified recommender model for large numbers of sharing scenarios; 2) how to handle with long-tail even cold start scenarios with limited training data; 3) how to incorporate social influence in order to make more accurate recommendations.

Textual explanations have proved to help improve user satisfaction on machine-made recommendations. However, current mainstream solutions loosely connect the learning of explanation with the learning of recommendation: for example, they are often separately modeled as rating prediction and content generation tasks. In this work, we propose to strengthen their connection by enforcing the idea of sentiment alignment between a recommendation and its corresponding explanation. At training time, the two learning tasks are joined by a latent sentiment vector, which is encoded by the recommendation module and used to make word choices for explanation generation. At both training and inference time, the explanation module is required to generate explanation text that matches sentiment predicted by the recommendation module. Extensive experiments demonstrate our solution outperforms a rich set of baselines in both recommendation and explanation tasks, especially on the improved quality of its generated explanations. More importantly, our user studies confirm our generated explanations help users better recognize the differences between recommended items and understand why an item is recommended.

Product query classification is the basic component for query understanding, which aims to classify the user queries into multiple categories under a predefined product category taxonomy for the E-commerce search engine. It is a challenging task due to the tremendous amount of product categories. And a slight modification to a query will change its corresponding categories entirely, e.g., appending the "button" to the query "shirt". The problem is more severe for the tail queries which lack enough supervision information from customers. Motivated by this phenomenon, this paper proposes to model the contrasting/similar relationships between such similar queries. Our framework is composed of a base model and an across-context attention module. The across-context attention module plays the role of deriving and extracting external information from these variant queries by predicting their categories. We conduct both offline and online experiments on the real-world E-commerce search engine. Experimental results demonstrate the effectiveness of our across-context attention module.

Intent recommendation, as a new type of recommendation service, is to recommend a predicted query to a user in the search box when the user lands on the homepage of an application without any input. Such an intent recommendation service has been widely used in e-commerce applications, such as Taobao and Amazon. The most difficult part is to accurately predict user’s search intent, so as to improve user’s search experience and reduce tedious typing especially on mobile phones. Existing methods mainly rely on user’s historical search behaviors to estimate user’s current intent, but they do not make full use of the feedback information between the user and the intent recommendation system. Essentially, feedback information is the key factor for capturing dynamics of user search intents in real time. Therefore, we propose a feedback interactive neural network (FINN) to estimate user’s potential search intent more accurately, by making full use of the feedback interaction with the following three parts: 1) Both positive feedback (PF) and negative feedback (NF) information are collected simultaneously. PF includes user’s search intent information that the user is interested in, such as the query used and the title clicked. NF indicates user’s search intent information that the user is not interested in, such as the query recommended by the system but not clicked by the user. 2) A filter-attention (FAT) structure is proposed to filter out the noisy feedback and get more accurate positive and negative intentions of users. 3) A multi-task learning is designed to match the correlation between the user’s search intent and query candidates, which can learn and recommend query candidates from user interests and disinterests associated with each user. Finally, extensive experiments have been conducted by comparing with state-of-the-art methods, and it shows that our FINN method can achieve the best performance using the Taobao mobile application dataset. In addition, online experimental results also show that our method improves the CTR by 8% and attracts more than 7.98% of users than the baseline.

The search engine plays a fundamental role in online e-commerce systems, to help users find the products they want from the massive product collections. Relevance is an essential requirement for e-commerce search, since showing products that do not match search query intent will degrade user experience. With the existence of vocabulary gap between user language of queries and seller language of products, measuring semantic relevance is necessary and neural networks are engaged to address this task. However, semantic relevance is different from click-through rate prediction in that no direct training signal is available. Most previous attempts learn relevance models from user click-through data that are cheap and abundant. Unfortunately, click behavior is noisy and misleading, which is affected by not only relevance but also factors including price, image and attractive titles. Therefore, it is challenging but valuable to learn relevance models from click-through data. In this paper, we propose a new relevance learning framework that concentrates on how to train a relevance model from the weak supervision of click-through data. Different from previous efforts that treat samples as either relevant or irrelevant, we construct more fine-grained samples for training. We propose a novel way to consider samples of different relevance confidence, and come up with a new training objective to learn a robust relevance model with desirable score distribution. The proposed model is evaluated on offline annotated data and online A/B testing, and it achieves both promising performance and high computational efficiency. The model has already been deployed online, serving the search traffic of Taobao for over a year.

In e-commerce search, vectorized matching is the most important approach besides lexical matching, where learning vector representations for entities (e.g., query, item, shop) plays a crucial role. In this work, we focus on vectorized search matching model for shop search in Taobao. Unlike item search, shop search is faced with serious behavior sparsity and long-tail problem. To tackle this, we take the first step to transfer knowledge from item search, i.e., leveraging items purchased under a query and the shops they belong to. Moreover, we propose a novel gated heterogeneous graph learning model (named GHL) to derive vector representations for entities. Both first-order and second-order proximity of queries and shops are exploited to fully mine the heterogeneous relationships. And to relieve long-tail phenomenon, we devise an innovative gated neighbor aggregation scheme where each type of entities (i.e., hot ones and long-tail ones) can benefit from the heterogeneous graph in an automatic way. Finally, the whole framework is jointly trained in an end-to-end fashion. Offline evaluation results on real-world data of Taobao shop search platform demonstrate that the proposed model outperforms existing graph based methods, and online A/B tests show that it is highly effective and achieves significant CTR improvements.

In this work, a new e-commerce search service named text-picture shopping guide (TPSG) is investigated and deployed to one of the most popular shopping platforms called Taobao. Different from traditional services that only contain text options, the TPSG provides pairs of text terms and user-friendly pictures for shopping guide, named text-picture options (TPOs). Instead of manually labeling pictures, we aim to automatically recommend personalized pictures in TPOs. To this end, we build a large-scale graph model on a great amount of data about users, pictures, and terms. Accordingly, a cross-graph convolution learning (CGCL) method is proposed to facilitate the accurate and efficient inference on the constructed graph. To separate the cue of personalized preferences of users to commodities, we factorize the entire mixture-relation graph involving attributes/relations of users and commodities into the user graph, the commodity graph, and the cross user-commodity graph which just characterizes the preferences. Further, we introduce powerful graph convolution to learn more effective representation of these graphs. To reduce the computation burden, specifically, we generalize graph convolution and propose a tensor graph convolution method to learn representation on cross graphs. We conduct extensive offline and online experiments on the large-scale datasets. The results show that the proposed CGCL is very effective and the TPOs recommendation method outperforms manual/advanced selection methods.

Shop search has become an increasingly important service provided by Taobao, the China's largest e-commerce platform. By using shop search, a user can easily identify the desired shop that provides a full-scale of relevant items matching his information need. With the tremendous growth of users and shops, shop search faces several unique challenging problems: 1) many shop names do not fully express what they sell, i.e., the semantic gap between user query and shop name; 2) due to the lack of user interactions, it is difficult to deliver a good search result for the long-tail queries and retrieve long-tail shops that are highly relevant to a query.

In this paper, we study the task of Query Auto-Completion (QAC), which is a very significant feature of modern search engines. In real industrial application, there always exist two major problems of QAC - weak personalization and unseen queries. To address these problems, we propose M2A, a multi-view multi-task attentive framework to learn personalized query auto-completion models. We propose a new Transformer-based hierarchical encoder to model different kinds of sequential behaviors, which can be seen as multiple distinct views of the user's searching history, and then a prefix-to-history attention mechanism is used to select the most relevant information to compose the final intention representation. To learn more informative representations, we propose to incorporate multi-task learning into the model training. Two different kinds of supervisory information provided by query logs are utilized at the same time by jointly training a CTR prediction model and a query generation model.

Most of ranking models are trained only with displayed items (most are hot items), but they are utilized to retrieve items in the entire space which consists of both displayed and non-displayed items (most are long-tail items). Due to the sample selection bias, the long-tail items lack sufficient records to learn good feature representations, ie data sparsity and cold start problems. The resultant distribution discrepancy between displayed and non-displayed items would cause poor long-tail performance. To this end, we propose an entire space adaptation model (ESAM) to address this problem from the perspective of domain adaptation (DA). ESAM regards displayed and non-displayed items as source and target domains respectively. Specifically, we design the attribute correlation alignment that considers the correlation between high-level attributes of the item to achieve distribution alignment. Furthermore, we introduce two effective regularization strategies, ie center-wise clustering andself-training to improve DA process. Without requiring any auxiliary information and auxiliary domains, ESAM transfers the knowledge from displayed items to non-displayed items for alleviating the distribution inconsistency. Experiments on two public datasets and a large-scale industrial dataset collected from Taobao demonstrate that ESAM achieves state-of-the-art performance, especially in the long-tail space. Besides, we deploy ESAM to the Taobao search engine, leading to significant improvement on online performance. The code is available at https://github.com/A-bone1/ESAM.git.

In a large recommender system, the products (or items) could be in many different categories or domains. Given two relevant domains (e.g., Book and Movie), users may have interactions with items in one domain but not in the other domain. To the latter, these users are considered as cold-start users. How to effectively transfer users' preferences based on their interactions from one domain to the other relevant domain, is the key issue in cross-domain recommendation. Inspired by the advances made in review-based recommendation, we propose to model user preference transfer at aspect-level derived from reviews. To this end, we propose a cross-domain recommendation framework via aspect transfer network for cold-start users (named CATN). CATN is devised to extract multiple aspects for each user and each item from their review documents, and learn aspect correlations across domains with an attention mechanism. In addition, we further exploit auxiliary reviews from like-minded users to enhance a user's aspect representations. Then, an end-to-end optimization framework is utilized to strengthen the robustness of our model. On real-world datasets, the proposed CATN outperforms SOTA models significantly in terms of rating prediction accuracy. Further analysis shows that our model is able to reveal user aspect connections across domains at a fine level of granularity, making the recommendation explainable.

In order to make the query retrieve much more related products, some query rewrite methods have been proposed to obtain a set of candidate queries which can infer users' search intents and reduce the vocabulary gap between the original query and title of related products. However, previous studies ignore that some candidate queries may change users' search intents and retrieve irrelevant products. As a result, users' search experience will be impacted significantly. To reduce this influence, we need to design a semantic matching model to determine whether the candidate query change the original query's search intents (semantics). In addition, building a semantic matching model faces the following challenges: 1) Queries are usually very short and have limited information. It is very hard to learn an effective semantic matching model with the textual information of queries and candidate queries. 2) In order to get a generalized and effective mode, sufficient data samples are required to train the model. However, the cost of labeling is very huge. In order to address the above challenges, we propose an active and deep semantic matching framework (ActiveMatch) which is composed of two components. One component is the deep semantic matching (DSM) model which can make full use of the search log information to enhance the representation of queries and candidate queries. Then, it can estimate the semantic similarity between the original query and the candidate query more accurately. The other component is an uncertainty and novelty sampling (UNS) strategy which selects the samples to label based on the difficulty of the model estimating and the probability of the occurrence of new words. It not only reduces the cost of labeling but also ensures the effectiveness of the model. The experimental results on the Taobao e-commercial search platform verify the effectiveness of our framework.

Synonym expansion is a technique that adds related words to search queries, which may lead to more relevant documents being retrieved, thus improving recall. There is extensive prior work on synonym expansion for web search, however very few studies have tackled its application for email search. Synonym expansion for private corpora like emails poses several unique research challenges. First, the emails are not shared across users, which precludes us from directly employing query-document bipartite graphs, which are standard in web search synonym expansion. Second, user search queries are of personal nature, and may not be generalizable across users. Third, the size of the underlying corpora from which the synonyms may be mined is relatively small (i.e., user's private email inbox) compared to the size of the web corpus. Therefore, in this paper, we propose a solution tailored to the challenges of synonym expansion for email search. We formulate it as a multi-view learning problem, and propose a novel embedding-based model that joins information from multiple sources to obtain the optimal synonym candidates. To demonstrate the effectiveness of the proposed technique, we evaluate our model using both explicit human ratings as well as a live experiment using the Gmail Search service, one of the world's largest email search engines.

Online shopping has been a habit of more and more people, while most users are unable to craft an informative query, and thus it often takes a long search session to satisfy their purchase intents. We present AliISA - a shopping assistant which offers users some tips to further specify their queries during a search session. With such an interactive search, users tend to find targeted items with fewer page requests, which often means a better user experience. Currently, AliISA assists tens of millions of users per day, earns more usage than existing systems, and consequently brings in a 5% improvement in CVR. In this paper, we present our system, describe the underlying techniques, and discuss our experience in stabilizing reinforcement learning under an E-commerce environment.

Query auto completion (QAC) is a prominent feature in modern search engines. High quality QAC substantially improves search experiences by helping users in typing less while submitting the queries. Many studies have been proposed to improve quality and relevance of the QAC methods from different perspectives, including leveraging contexts in long term and short term query histories, investigating the temporal information for time-sensitive QAC, and analyzing user behaviors. Although these studies have shown the context, temporal, and user behavior data carry valuable information, most existing QAC approaches do not fully exploit or even completely ignore these information. We propose a novel Hawkes process based QAC algorithm, comprehensively taking into account the context, temporal, and position of the clicked recommended query completions (a type of user behavior data), for reliable query completion prediction. Our understanding of ranking query completions is consistent with the mathematical rationale of Hawke process; such a coincidence in turn validates our motivation of using Hawkes process for QAC. We also develop an efficient inference algorithm to compute the optimal solutions of the proposed QAC algorithm. The proposed method is evaluated on two real-world benchmark data in comparison with state-of-art methods, and the obtained experiments clearly demonstrate their effectiveness.

Contextual data plays an important role in modeling search engine users' behaviors on both query auto-completion (QAC) log and normal query (click) log. User's recent search history on each log has been widely studied individually as the context to benefit the modeling of users' behaviors on that log. However, there is no existing work that explores or incorporates both logs together for contextual data. As QAC and click logs actually record users' sequential behaviors while interacting with a search engine, the available context of a user's current behavior based on the same type of log can be strengthened from the user's recent search history shown on the other type of log. Our paper proposes to model users' behaviors on both QAC and click logs simultaneously by utilizing both logs as the contextual data of each other. The key idea is to capture the correlation between users' behavior patterns on both logs. We model such correlation through a novel probabilistic model based on the Latent Dirichlet allocation (LDA) model. The learned users' behavior patterns on both logs are utilized to address not only the application of query auto-completion on QAC logs, but also the click prediction and relevance ranking of web documents on click logs. Experiments on real-world logs demonstrate the effectiveness of the proposed model on both applications.

Query auto-completion (QAC) is widely used by modern search engines to assist users by predicting their intended queries. Most QAC approaches rely on deterministic batch learning algorithms trained from past query log data. However, query popularities keep changing all the time and QAC operates in a real-time scenario where users interact with the search engine continually. So, ideally, QAC must be timely and adaptive enough to reflect time-sensitive changes in an online fashion. Second, due to the vertical position bias, a query suggestion with a higher rank tends to attract more clicks regardless of user's original intention. Hence, in the long run, it is important to place some lower ranked yet potentially more relevant queries to higher positions to collect more valuable user feedbacks. In order to tackle these issues, we propose to formulate QAC as a ranked Multi-Armed Bandits (MAB) problem which enjoys theoretical soundness. To utilize prior knowledge from query logs, we propose to use Bayesian inference and Thompson Sampling to solve this MAB problem. Extensive experiments on large scale datasets show that our QAC algorithm has the capacity to adaptively learn temporal trends, and outperforms existing QAC algorithms in ranking qualities.

Search engines play a crucial role in our daily lives. Relevance is the core problem of a commercial search engine. It has attracted thousands of researchers from both academia and industry and has been studied for decades. Relevance in a modern search engine has gone far beyond text matching, and now involves tremendous challenges. The semantic gap between queries and URLs is the main barrier for improving base relevance. Clicks help provide hints to improve relevance, but unfortunately for most tail queries, the click information is too sparse, noisy, or missing entirely. For comprehensive relevance, the recency and location sensitivity of results is also critical. In this paper, we give an overview of the solutions for relevance in the Yahoo search engine. We introduce three key techniques for base relevance -- ranking functions, semantic matching features and query rewriting. We also describe solutions for recency sensitive relevance and location sensitive relevance. This work builds upon 20 years of existing efforts on Yahoo search, summarizes the most recent advances and provides a series of practical relevance solutions. The performance reported is based on Yahoo's commercial search engine, where tens of billions of urls are indexed and served by the ranking system.

No abstract available.

Search tasks in users' query sequences are dynamic and interconnected. The formulation of search tasks can be influenced by multiple latent factors such as user characteristics, product features and search interactions, which makes search task identification a challenging problem. In this paper, we propose an unsupervised approach to identify search tasks via topic membership along with topic transition probabilities, thus it becomes possible to interpret how user's search intent emerges and evolves over time. Moreover, a novel hidden semi-Markov model is introduced to model topic transitions by considering not only the semantic information of queries but also the latent search factors originated from user search behaviors. A variational inference algorithm is developed to identify remarkable search behavior patterns, typical topic transition tracks, and the topic membership of each query from query logs. The learned topic transition tracks and the inferred topic memberships enable us to identify both small search tasks, where a user searches the same topic, and big search tasks, where a user searches a series of related topics. We extensively evaluate the proposed approach and compare with several state-of-the-art search task identification methods on both synthetic and real-world query log data, and experimental results illustrate the effectiveness of our proposed model.

We study the new mobile query auto-completion (QAC) problem to exploit mobile devices' exclusive signals, such as those related to mobile applications (apps). We propose AppAware, a novel QAC model using installed app and recently opened app signals to suggest queries for matching input prefixes on mobile devices. To overcome the challenge of noisy and voluminous signals, AppAware optimizes composite objectives with a lighter processing cost at a linear rate of convergence. We conduct experiments on a large commercial data set of mobile queries and apps. Installed app and recently opened app signals consistently and significantly boost the accuracy of various baseline QAC models on mobile devices.

Query auto-completion (QAC) plays an important role in assisting users typing less while submitting a query. The QAC engine generally offers a list of suggested queries that start with a user's input as a prefix, and the list of suggestions is changed to match the updated input after the user types each keystroke. Therefore rich user interactions can be observed along with each keystroke until a user clicks a suggestion or types the entire query manually. It becomes increasingly important to analyze and understand users' interactions with the QAC engine, to improve its performance. Existing works on QAC either ignored users' interaction data, or assumed that their interactions at each keystroke are independent from others. Our paper pays high attention to users' sequential interactions with a QAC engine in and across QAC sessions, rather than users' interactions at each keystroke of each QAC session separately. Analyzing the dependencies in users' sequential interactions improves our understanding of the following three questions: 1) how is a user's skipping/viewing move at the current keystroke influenced by that at the previous keystroke? 2) how to improve search engines' query suggestions at short keystrokes based on those at latter long keystrokes? and 3) facing a targeted query shown in the suggestion list, why does a user decide to continue typing rather than click the intended suggestion? We propose a probabilistic model that addresses those three questions in a unified way, and illustrate how the model determines users' final click decisions. By comparing with state-of-the-art methods, our proposed model does suggest queries that better satisfy users' intents.

Query auto-completion (QAC) facilitates user query composition by suggesting queries given query prefix inputs. In 2014, global users of Yahoo! Search saved more than 50% keystrokes when submitting English queries by selecting suggestions of QAC. Users' preference of queries can be inferred during user-QAC interactions, such as dwelling on suggestion lists for a long time without selecting query suggestions ranked at the top. However, the wealth of such implicit negative feedback has not been exploited for designing QAC models. Most existing QAC models rank suggested queries for given prefixes based on certain relevance scores.

We consider a search task as a set of queries that serve the same user information need. Analyzing search tasks from user query streams plays an important role in building a set of modern tools to improve search engine performance. In this paper, we propose a probabilistic method for identifying and labeling search tasks based on the following intuitive observations: queries that are issued temporally close by users in many sequences of queries are likely to belong to the same search task, meanwhile, different users having the same information needs tend to submit topically coherent search queries. To capture the above intuitions, we directly model query temporal patterns using a special class of point processes called Hawkes processes, and combine topic models with Hawkes processes for simultaneously identifying and labeling search tasks. Essentially, Hawkes processes utilize their self-exciting properties to identify search tasks if influence exists among a sequence of queries for individual users, while the topic model exploits query co-occurrence across different users to discover the latent information needed for labeling search tasks. More importantly, there is mutual reinforcement between Hawkes processes and the topic model in the unified model that enhances the performance of both. We evaluate our method based on both synthetic data and real-world query log data. In addition, we also apply our model to query clustering and search task identification. By comparing with state-of-the-art methods, the results demonstrate that the improvement in our proposed approach is consistent and promising.

Query auto-completion (QAC) facilitates faster user query input by predicting users' intended queries. Most QAC algorithms take a learning-based approach to incorporate various signals for query relevance prediction. However, such models are trained on simulat- ed user inputs from query log data. The lack of real user interaction data in the QAC process prevents them from further improving the QAC performance. In this work, for the first time we collect a high-resolution QAC query log that records every keystroke in a QAC session. Based on this data, we discover two user behaviors, namely the horizontal skipping bias and vertical position bias which are crucial for rele- vance prediction in QAC. In order to better explain them, we pro- pose a novel two-dimensional click model for modeling the QAC process with emphasis on these behaviors. Extensive experiments on our QAC data set from both PC and mobile devices demonstrate that our proposed model can accurate- ly explain the users' behaviors in interacting with a QAC system, and the resulting relevance model significant improves the QAC performance over existing click models. Furthermore, the learned knowledge about the skipping behavior can be effectively incorpo- rated into existing learning-based models to further improve their performance.

With the development of social media and social networks, user-generated content, like forums, blogs and comments, are not only getting richer, but also ubiquitously interconnected with many other objects and entities, forming a heterogeneous information network between them. Sentiment analysis on such kinds of data can no longer ignore the information network, since it carries a lot of rich and valuable information, explicitly or implicitly, where some of them can be observed while others are not. In this paper, we propose a novel information network-based framework which can infer hidden similarity and dissimilarity between users by exploring similar and opposite opinions, so as to improve post-level and user-level sentiment classification in the same time. More specifically, we develop a new meta path-based measure for inferring pseudo-friendship as well as dissimilarity between users, and propose a semi-supervised refining model by encoding similarity and dissimilarity from both user-level and post-level relations. We extensively evaluate the proposed approach and compare with several state-of-the-art techniques on two real-world forum datasets. Experimental results show that our proposed model with 10.5% labeled samples can achieve better performance than a traditional supervised model trained on 61.7% data samples.

Clustering is an important technique for mining the intrinsic community structures in networks. The density-based network clustering method is able to not only detect communities of arbitrary size and shape, but also identify hubs and outliers. However, it requires manual parameter specification to define clusters, and is sensitive to the parameter of density threshold which is difficult to determine. Furthermore, many real-world networks exhibit a hierarchical structure with communities embedded within other communities. Therefore, the clustering result of a global parameter setting cannot always describe the intrinsic clustering structure accurately. In this paper, we introduce a novel density-based network clustering method, called graph-skeleton-based clustering (gSkeletonClu). By projecting an undirected network to its core-connected maximal spanning tree, the clustering problem can be converted to detect core connectivity components on the tree. The density-based clustering of a specific parameter setting and the hierarchical clustering structure both can be efficiently extracted from the tree. Moreover, it provides a convenient way to automatically select the parameter and to achieve the meaningful cluster tree in a network. Extensive experiments on both real-world and synthetic networks demonstrate the superior performance of gSkeletonClu for effective and efficient density-based clustering.

Users' locations are important to many applications such as targeted advertisement and news recommendation. In this paper, we focus on the problem of profiling users' home locations in the context of social network (Twitter). The problem is nontrivial, because signals, which may help to identify a user's location, are scarce and noisy. We propose a unified discriminative influence model, named as UDI, to solve the problem. To overcome the challenge of scarce signals, UDI integrates signals observed from both social network (friends) and user-centric data (tweets) in a unified probabilistic framework. To overcome the challenge of noisy signals, UDI captures how likely a user connects to a signal with respect to 1) the distance between the user and the signal, and 2) the influence scope of the signal. Based on the model, we develop local and global location prediction methods. The experiments on a large scale data set show that our methods improve the state-of-the-art methods by 13%, and achieve the best performance.

With the development of Web applications, textual documents are not only getting richer, but also ubiquitously interconnected with users and other objects in various ways, which brings about text-rich heterogeneous information networks. Topic models have been proposed and shown to be useful for document analysis, and the interactions among multi-typed objects play a key role at disclosing the rich semantics of the network. However, most of topic models only consider the textual information while ignore the network structures or can merely integrate with homogeneous networks. None of them can handle heterogeneous information network well. In this paper, we propose a novel topic model with biased propagation (TMBP) algorithm to directly incorporate heterogeneous information network with topic modeling in a unified way. The underlying intuition is that multi-typed objects should be treated differently along with their inherent textual information and the rich semantics of the heterogeneous information network. A simple and unbiased topic propagation across such a heterogeneous network does not make much sense. Consequently, we investigate and develop two biased propagation frameworks, the biased random walk framework and the biased regularization framework, for the TMBP algorithm from different perspectives, which can discover latent topics and identify clusters of multi-typed objects simultaneously. We extensively evaluate the proposed approach and compare to the state-of-the-art techniques on several datasets. Experimental results demonstrate that the improvement in our proposed approach is consistent and promising.

In this paper, we propose a joint probabilistic topic model for simultaneously modeling the contents of multi-typed objects of a heterogeneous information network. The intuition behind our model is that different objects of the heterogeneous network share a common set of latent topics so as to adjust the multinomial distributions over topics for different objects collectively. Experimental results demonstrate the effectiveness of our approach for the tasks of topic modeling and object clustering.

Community detection is an important task for mining the structure and function of complex networks. Generally, there are several different kinds of nodes in a network which are cluster nodes densely connected within communities, as well as some special nodes like hubs bridging multiple communities and outliers marginally connected with a community. In addition, it has been shown that there is a hierarchical structure in complex networks with communities embedded within other communities. Therefore, a good algorithm is desirable to be able to not only detect hierarchical communities, but also identify hubs and outliers. In this paper, we propose a parameter-free hierarchical network clustering algorithm SHRINK by combining the advantages of density-based clustering and modularity optimization methods. Based on the structural connectivity information, the proposed algorithm can effectively reveal the embedded hierarchical community structure with multiresolution in large-scale weighted undirected networks, and identify hubs and outliers as well. Moreover, it overcomes the sensitive threshold problem of density-based clustering algorithms and the resolution limit possessed by other modularity-based methods. To illustrate our methodology, we conduct experiments with both real-world and synthetic datasets for community detection, and compare with many other baseline methods. Experimental results demonstrate that SHRINK achieves the best performance with consistent improvements.

Community detection is an important task for mining the structure and function of complex networks. Many pervious approaches are difficult to detect communities with arbitrary size and shape, and are unable to identify hubs and outliers. A recently proposed network clustering algorithm, SCAN, is effective and can overcome this difficulty. However, it depends on a sensitive parameter: minimum similarity threshold ε, but provides no automated way to find it. In this paper, we propose a novel density-based network clustering algorithm, called gSkeletonClu (graph-skeleton based clustering). By projecting a network to its Core-Connected Maximal Spanning Tree (CCMST), the network clustering problem is converted to finding core-connected components in the CCMST. We discover that all possible values of the parameter ε lie in the edge weights of the corresponding CCMST. By means of tree divisive or agglomerative clustering, our algorithm can find the optimal parameter ε and detect communities, hubs and outliers in large-scale undirected networks automatically without any user interaction. Extensive experiments on both real-world and synthetic networks demonstrate the superior performance of gSkeletonClu over the baseline methods.

Expertise retrieval has received increased interests in recent years, whose task is to suggest people with relevant expertise. Motivated by the observation that communities could provide valuable insight and distinctive information, we investigate two community-aware strategies to enhance expertise retrieval. We first propose a new smoothing method using the community context instead of the whole collection for statistical language model in the document-based model. Furthermore, a query-sensitive AuthorRank is proposed to model the authors' authorities according to the community co-authorship networks, and then an adaptive ranking refinement method is developed to further enhance expertise retrieval. Experimental results demonstrate the effectiveness and robustness of both community-aware strategies.

This paper addresses the issue of social recommendation based on collaborative filtering (CF) algorithms. Social recommendation emphasizes utilizing various attributes information and relations in social networks to assist recommender systems. Although recommendation techniques have obtained distinct developments over the decades, traditional CF algorithms still have these following two limitations: (1) relational dependency within predictions, an important factor especially when the data is sparse, is not being utilized effectively; and (2) straightforward methods for combining features like linear integration suffer from high computing complexity in learning the weights by enumerating the whole value space, making it difficult to combine various information into an unified approach. In this paper, we propose a novel model, Multi-scale Continuous Conditional Random Fields (MCCRF), as a framework to solve above problems for social recommendations. In MCCRF, relational dependency within predictions is modeled by the Markov property, thus predictions are generated simultaneously and can help each other. This strategy has never been employed previously. Besides, diverse information and relations in social network can be modeled by state and edge feature functions in MCCRF, whose weights can be optimized globally. Thus both problems can be solved under this framework. In addition, We propose to utilize Markov chain Monte Carlo (MCMC) estimation methods to solve the difficulties in training and inference processes of MCCRF. Experimental results conducted on two real world data have demonstrated that our approach outperforms traditional CF algorithms. Additional experiments also show the improvements from the two factors of relational dependency and feature combination, respectively.

Recently many data types arising from data mining and Web search applications can be modeled as bipartite graphs. Examples include queries and URLs in query logs, and authors and papers in scientific literature. However, one of the issues is that previous algorithms only consider the content and link information from one side of the bipartite graph. There is a lack of constraints to make sure the final relevance of the score propagation on the graph, as there are many noisy edges within the bipartite graph. In this paper, we propose a novel and general Co-HITS algorithm to incorporate the bipartite graph with the content information from both sides as well as the constraints of relevance. Moreover, we investigate the algorithm based on two frameworks, including the iterative and the regularization frameworks, and illustrate the generalized Co-HITS algorithm from different views. For the iterative framework, it contains HITS and personalized PageRank as special cases. In the regularization framework, we successfully build a connection with HITS, and develop a new cost function to consider the direct relationship between two entity sets, which leads to a significant improvement over the baseline method. To illustrate our methodology, we apply the Co-HITS algorithm, with many different settings, to the application of query suggestion by mining the AOL query log data. Experimental results demonstrate that CoRegu-0.5 (i.e., a model of the regularization framework) achieves the best performance with consistent and promising improvements.

Query log analysis has received substantial attention in recent years, in which the click graph is an important technique for describing the relationship between queries and URLs. State-of-the-art approaches based on the raw click frequencies for modeling the click graph, however, are not noise-eliminated. Nor do they handle heterogeneous query-URL pairs well. In this paper, we investigate and develop a novel entropy-biased framework for modeling click graphs. The intuition behind this model is that various query-URL pairs should be treated differently, i.e., common clicks on less frequent but more specific URLs are of greater value than common clicks on frequent and general URLs. Based on this intuition, we utilize the entropy information of the URLs and introduce a new concept, namely the inverse query frequency (IQF), to weigh the importance (discriminative ability) of a click on a certain URL. The IQF weighting scheme is never explicitly explored or statistically examined for any bipartite graphs in the information retrieval literature. We not only formally define and quantify this scheme, but also incorporate it with the click frequency and user frequency information on the click graph for an effective query representation. To illustrate our methodology, we conduct experiments with the AOL query log data for query similarity analysis and query suggestion tasks. Experimental results demonstrate that considerable improvements in performance are obtained with our entropy-biased models. Moreover, our method can also be applied to other bipartite graphs.

Recently the re-ranking algorithms have been quite popular for web search and data mining. However, one of the issues is that those algorithms treat the content and link information individually. Inspired by graph-based machine learning algorithms, we propose a novel and general framework to model the re-ranking algorithm, by regularizing the smoothness of ranking scores over the graph, along with a regularizer on the initial ranking scores (which are obtained by the base ranker). The intuition behind the model is the global consistency over the graph: similar entities are likely to have the same ranking scores with respect to a query. Our approach simultaneously incorporates the content with other explicit or implicit link information in a latent space graph. Then an effective unified re-ranking algorithm is performed on the graph with respect to the query. To illustrate our methodology, we apply the framework to literature retrieval and expert finding applications on DBLP bibliography data. We compare the proposed method with the initial language model method and another PageRank-style re-ranking method. Also, we evaluate the proposed method with varying graphs and settings. Experimental results show that the improvement in our proposed method is consistent and promising.

Finding relevant experts in a specific field is often crucial for consulting, both in industry and in academia. The aim of this paper is to address the expert-finding task in a real world academic field. We present three models for expert finding based on the large-scale DBLP bibliography and Google scholar for data supplementation. The first, a novel weighted language model, models an expert candidate based on the relevance and importance of associated documents by introducing a document prior probability, and achieves much better results than the basic language model. The second, a topic-based model, represents each candidate as a weighted sum of multiple topics, whilst the third, a hybrid model, combines the language model and the topic-based model. We evaluate our system using a benchmark dataset based on human relevance judgments of how well the expertise of proposed experts matches a query topic. Evaluation results show that our hybrid model outperforms other models in nearly all metrics.