Sequential recommendation aims to model users' evolving preferences based on their historical interactions. Recent advances leverage Transformer-based architectures to capture global dependencies, but existing methods often suffer from high computational overhead, primarily due to discontinuous memory access in temporal encoding and dense attention over long sequences. To address these limitations, we propose FuXi-γ, a novel sequential recommendation framework that improves both effectiveness and efficiency through principled architectural design. FuXi-γ adopts a decoder-only Transformer structure and introduces two key innovations: (1) An exponential-power temporal encoder that encodes relative temporal intervals using a tunable exponential decay function inspired by the Ebbinghaus forgetting curve. This encoder enables flexible modeling of both short-term and long-term preferences while maintaining high efficiency through continuous memory access and pure matrix operations. (2) A diagonal-sparse positional mechanism that prunes low-contribution attention blocks using a diagonal-sliding strategy guided by the persymmetry of Toeplitz matrix. Extensive experiments on four real-world datasets demonstrate that FuXi-γ achieves state-of-the-art performance in recommendation quality, while accelerating training by up to 4.74× and inference by up to 6.18×, making it a practical and scalable solution for long-sequence recommendation. Code: https://github.com/Yeedzhi/FuXi-gamma.

Interactive recommendation is a typical information-seeking task that allows users to interactively express their needs through natural language and obtain personalized recommendations. Large language model-powered (LLM-powered) agents have become a new paradigm in interactive recommendations, effectively capturing users' real-time needs and enhancing personalized experiences. However, due to limited planning and generalization capabilities, existing formulations of LLM-powered interactive recommender agents struggle to effectively address diverse and complex user intents, such as intuitive, unrefined, or occasionally ambiguous requests. To tackle this challenge, we propose a novel ThoughtAugmented Interactive Recommender Agent system (TAIRA) that addresses complex user intents through distilled thought patterns. Specifically, TAIRA is designed as an LLM-powered multi-agent system featuring a manager agent that orchestrates recommendation tasks by decomposing user needs and planning subtasks, with its planning capacity strengthened through Thought Pattern Distillation (TPD), a thought-augmentation method that extracts high-level thoughts from the agent's and human experts' experiences. Through comprehensive experiments conducted across multiple designed datasets, TAIRA exhibits significantly enhanced performance compared to existing methods. Notably, TAIRA's thought augmentation strategies endow the agent system with the ability to solve complex tasks while generalizing effectively on novel tasks, validating its potential as a foundational framework for agent systems, particularly in complex user intent scenarios.

Generative recommendation casts recommendation as conditional sequence generation over text- or token-based representations and has shown strong promise in industrial systems. However, keeping such models up to date in dynamic environments is difficult: full retraining on sliding windows is expensive and slow, while incremental fine-tuning on recent data may introduce distributional bias and catastrophic forgetting.

Personalization is becoming a core capability of modern AI systems. It enables systems to adapt their responses and behaviors according to individual users' preferences, contexts, and goals. Recent research has focused on Retrieval-Augmented Generation (RAG) and its development toward more advanced agent-based frameworks to improve user satisfaction in personalized settings. In this tutorial, we provide a systematic overview of how personalization can be incorporated into the three main stages of RAG: pre-retrieval, retrieval, and generation. We then extend the discussion to personalized LLM-based agents, which build on RAG by adding agent capabilities such as user understanding, personalized planning and execution, and adaptive response generation. For both RAG-based and agent-based approaches, we present clear definitions, review recent research, and summarize commonly used datasets and evaluation metrics. We also discuss key challenges, current limitations, and potential future research directions. An updated list of related papers and resources is available at our GitHub repository. https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent. Further updates for this tutorial will be uploaded on the homepage. https://applied-machine-learning-lab.github.io/SIGIR2026_PRAG_Tutorial.

Table Retrieval (TR) has traditionally been formulated as an ad-hoc retrieval problem, where relevance is primarily determined by topical semantic similarity. With the growing adoption of LLM-based agentic systems, access to structured data is increasingly instruction-driven, where relevance is conditional on explicit content and schema constraints rather than topical similarity alone. We therefore formalize Instruction-Following Table Retrieval (IFTR), a new task that requires models to jointly satisfy topical relevance and fine-grained instruction constraints. We identify two core challenges in IFTR: (i) sensitivity to content scope, such as inclusion and exclusion constraints, and (ii) awareness of schema-grounded requirements, including column semantics and representation granularity--capabilities largely absent in existing retrievers. To support systematic evaluation, we introduce FollowTable, the first large-scale benchmark for IFTR, constructed via a taxonomy-driven annotation pipeline. We further propose a new metric, termed the Instruction Responsiveness Score, to evaluate whether retrieval rankings consistently adapt to user instructions relative to a topic-only baseline. Our results indicate that existing retrieval models struggle to follow fine-grained instructions over tabular data. In particular, they exhibit systematic biases toward surface-level semantic cues and remain limited in handling schema-grounded constraints, highlighting substantial room for future improvements.

Deep Research agents driven by LLMs have automated the scholarly discovery pipeline, from planning and query formulation to iterative web exploration. Yet they remain constrained by a static, ''one-size-fits-all'' retrieval paradigm. Current systems fail to adaptively adjust the depth and breadth of exploration based on the user's existing expertise or latent interests, frequently resulting in reports that are either redundant for experts or overly dense for novices. To address this, we introduce Personalized Deep Research (PDR), a framework that integrates dynamic user context into the core retrieval-reasoning loop. Rather than treating personalization as a post-hoc formatting step, PDR unifies user profile modeling with iterative query development, dual-stage (private/public) retrieval, and context-aware synthesis. This allows the system to autonomously align research sub-goals with user intent and optimize the stopping criteria for evidence collection. To facilitate benchmarking, we release the PDR Dataset, covering four realistic user tasks, and propose a hybrid evaluation framework combining lexical metrics with LLM-based judgments to assess factual accuracy and personalization alignment. Experimental results against commercial baselines demonstrate that PDR significantly improves retrieval utility and report relevance, effectively bridging the gap between generic information retrieval and personalized knowledge acquisition. The resource is available to the public at~ https://github.com/Applied-Machine-Learning-Lab/SIGIR2026_PDR.

Although generative recommenders demonstrate improved performance with longer sequences, their real-time deployment is hindered by substantial computational costs. To address this challenge, we propose a simple yet effective method for compressing long-term user histories by leveraging inherent item categorical features, thereby preserving user interests while enhancing efficiency. Experiments on two large-scale datasets demonstrate that, compared to the influential HSTU model, our approach achieves up to a 6× reduction in computational cost and up to 39% higher accuracy at comparable cost (i.e., similar sequence length). The source code will be available at https://github.com/Genemmender/CAUSE.

Deep Research systems have revolutionized how LLMs solve complex questions through iterative reasoning and evidence gathering. However, current systems remain fundamentally constrained to textual web data, overlooking the vast knowledge embedded in multimodal documents: scientific papers, technical reports, and financial documents where critical information exists in figures, tables, charts, and equations. Processing such documents demands sophisticated parsing to preserve visual semantics, intelligent chunking to maintain structural coherence, and adaptive retrieval across modalities, which are capabilities absent in existing systems. In response, we present Doc-Researcher, a unified system that bridges this gap through three integrated components: (i) deep multimodal parsing that preserves layout structure and visual semantics while creating multi-granular representations from chunk to document level, (ii) systematic retrieval architecture supporting text-only, vision-only, and hybrid paradigms with dynamic granularity selection, and (iii) iterative multi-agent workflows that decompose complex queries, progressively accumulate evidence, and synthesize comprehensive answers across documents and modalities. To enable rigorous evaluation, we introduce M4DocBench, the first benchmark for Multi-modal, Multi-hop, Multi-document, and Multi-turn deep research. Featuring 158 expert-annotated questions with complete evidence chains across 304 documents, M4DocBench tests capabilities that existing benchmarks cannot assess. Experiments demonstrate that Doc-Researcher achieves 50.6% accuracy, 3.4× better than state-of-the-art baselines, validating that effective document research requires not just better retrieval, but fundamentally deep parsing that preserve multimodal integrity and support iterative research. Our work establishes a new paradigm for conducting deep research on multimodal document collections.

Deep search agents, which autonomously iterate through multi-turn web-based reasoning, represent a promising paradigm for complex information-seeking tasks. However, current agents suffer from critical inefficiency: they conduct excessive searches as they cannot accurately judge when to stop searching and start answering. This stems from outcome-centric training that prioritize final results over the search process itself. We identify the root cause as misaligned decision boundaries, the threshold determining when accumulated information suffices to answer. This causes over-search (redundant searching despite sufficient knowledge) and under-search (premature termination yielding incorrect answers). To address these errors, we propose a comprehensive framework comprising two key components. First, we introduce causal intervention-based diagnosis that identifies boundary errors by comparing factual and counterfactual trajectories at each decision point. Second, we develop Decision Boundary Alignment for Deep Search agents (DAS), which constructs preference datasets from causal feedback and aligns policies via preference optimization. Experiments on public datasets demonstrate that decision boundary errors are pervasive across state-of-the-art agents. Our DAS method effectively calibrates these boundaries, mitigating both over-search and under-search to achieve substantial gains in accuracy and efficiency. Our code and data are publicly available at: https://github.com/Applied-Machine-Learning-Lab/WWW2026-DAS. © 2026 Owner/Author.

Personalization has become an essential capability in modern AI systems, enabling customized interactions that align with individual user preferences, contexts, and goals. Recent research has increasingly concentrated on Retrieval-Augmented Generation (RAG) frameworks and their evolution into more advanced agent-based architectures within personalized settings to enhance user satisfaction. Building on this foundation, this survey systematically examines personalization across the three core stages of RAG: pre-retrieval, retrieval, and generation. Beyond RAG, we further extend its capabilities into the realm of Personalized LLM-based Agents, which enhance traditional RAG systems with agentic functionalities, including user understanding, personalized planning and execution, and dynamic generation. For both personalization in RAG and agent-based personalization, we provide formal definitions, conduct a comprehensive review of recent literature, and summarize key datasets and evaluation metrics. Additionally, we discuss fundamental challenges, limitations, and promising research directions in this evolving field. Relevant papers and resources are continuously updated at the Github Repo ( https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent ).

Efficient and effective modeling of feature interactions is key to large-scale Click-Through Rate (CTR) prediction. Although existing feature interaction methods have improved the model accuracy, their computational consumption still increase exponentially with the number of feature fields and become severe efficiency bottleneck in real-world industrial scenarios. To address the issues, we propose an E fficient and E ffective NET work for large-scale CTR prediction named EENet . EENet presents a new alternating stacking architecture of implicit and explicit interaction layers, and each implicit layer in EENet can reduce both local computational and parameter load remarkably. EENet also designs a unified explicit interaction operation which can only use simple matrix multiplication to capture field-wise patterns. Moreover, the order of multiplications in EENet is rearranged to further decrease the computational complexity from quadratic to linear with respect to the number of feature fields. EENet thus can support the high efficiency in real-practice industrial scenarios with hundreds of feature fields. A set of extensive experiments is performed on two public datasets and one industrial dataset for effectiveness evaluation, and five larger-scale synthetic datasets for efficiency evaluation. The results highlight that our EENet can significantly outperform the state-of-the-art models in terms of both efficiency and scalability, while also maintaining superior effectiveness. Compared with DCNv2 and FiBiNet, EENet achieves 8.06 \(\times\) and 36.72 \(\times\) efficiency improvements in training, and 2.02 \(\times\) and 48.88 \(\times\) improvements in inference, respectively. Our solution and source code are available at https://github.com/Yeedzhi/EENet .

Sequential recommendation (SR), as an important branch of recommendation systems, has garnered significant attention due to its substantial commercial value. This has inspired some researchers to draw from the successful experiences of large language models to develop scaling laws for SR. However, the improvements brought by parameter expansion often reach a limit when the data scale is fixed. We have observed that existing deep learning sequence methods are typically seen as learning a unified pattern of user interactions, as they apply the same model for inference across different users, which often leads to the neglect of individual user behavior patterns. To address this, we propose conducting an independent analysis of each user's interaction sequence in SR. We initially developed the PCRec-simple, which uses KL divergence to perform a one-time optimization on each sequence after training, demonstrating that optimizing individual sequences can provide additional insights and overcome the performance bottleneck after scaling laws. Subsequently, we introduce PCRec, a sequential recommendation model that integrates real-time inference of hidden states into the model. It applies KL divergence optimization during the forward process, allowing for end-to-end optimization and addressing issues of robustness, parallelism, and optimization stability. Extensive experiments on real-world datasets show that PCRec significantly outperforms the current state-of-the-art methods. The code can be found at https://github.com/USTC-StarTeam/PCRec.

Click-through Rate (CTR) prediction is crucial for online personalization platforms. Recent advancements have shown that modeling rich user behaviors can significantly improve the performance of CTR prediction. Current long-term user behavior modeling algorithms predominantly follow two cascading stages. The first stage retrieves subsequence related to the target item from the long-term behavior sequence, while the second stage models the relationship between the subsequence and the target item. Despite significant progress, these methods have two critical flaws. First, the retrieval query typically includes only target item information, limiting the ability to capture the user's diverse interests. Second, relational information, such as sequential and interactive information within the subsequence, is frequently overlooked. Therefore, it requires to be further mined to more accurately model user interests.

Cloud-device collaboration leverages on-cloud Large Language Models (LLMs) for handling public user queries and on-device Small Language Models (SLMs) for processing private user data, collectively forming a powerful and privacy-preserving solution.However, existing approaches often fail to fully leverage the scalable problem-solving capabilities of on-cloud LLMs while underutilizing the advantage of on-device SLMs in accessing and processing personalized data.This leads to two interconnected issues: 1) Limited utilization of the problem-solving capabilities of on-cloud LLMs, which fail to align with personalized user-task needs, and 2) Inadequate integration of user data into on-device SLM responses, resulting in mismatches in contextual user information.In this paper, we propose a Leader-Subordinate Retrieval framework for Privacy-preserving cloud-device collaboration (LSRP), a novel solution that bridges these gaps by: 1) enhancing on-cloud * Contributed equally to this work.

Click-through rate (CTR) prediction is a critical task in online advertising and recommender systems, relying on effective modeling of feature interactions.Explicit interactions capture predefined relationships, such as inner products, but often suffer from data sparsity, while implicit interactions excel at learning complex patterns through non-linear transformations but lack inductive biases for efficient low-order modeling.Existing two-stream architectures integrate these paradigms but face challenges such as limited information sharing, gradient imbalance, and difficulty preserving low-order signals in sparse CTR data.We propose a novel framework, Dynamic Low-Order-Aware Fusion (DLF), which addresses these limitations through two key components: a Residual-Aware Low-Order Interaction Network (RLI) and a Network-Aware Attention Fusion Module (NAF).RLI explicitly preserves low-order signals while mitigating redundancy from residual connections, and NAF dynamically integrates explicit and implicit representations at each layer, enhancing information sharing and alleviating gradient imbalance.Together, these innovations balance low-order and high-order interactions, improving model expressiveness.Extensive experiments on public datasets demonstrate that DLF achieves

In recommendation systems, the traditional multi-stage paradigm, which includes retrieval and ranking, often suffers from information loss between stages and diminishes performance. Recent advances in generative models, inspired by natural language processing, suggest the potential for unifying these stages to mitigate such loss. This paper presents the Unified Generative Recommendation Framework (UniGRF), a novel approach that integrates retrieval and ranking into a single generative model. By treating both stages as sequence generation tasks, UniGRF enables sufficient information sharing without additional computational costs, while remaining model-agnostic. To enhance inter-stage collaboration, UniGRF introduces a ranking-driven enhancer module that leverages the precision of the ranking stage to refine retrieval processes, creating an enhancement loop. Besides, a gradient-guided adaptive weighter is incorporated to dynamically balance the optimization of retrieval and ranking, ensuring synchronized performance improvements. Extensive experiments demonstrate that UniGRF significantly outperforms existing models on benchmark datasets, confirming its effectiveness in facilitating information transfer. Ablation studies and further experiments reveal that UniGRF not only promotes efficient collaboration between stages but also achieves synchronized optimization. UniGRF provides an effective, scalable, and compatible framework for generative recommendation systems.

Abstract Educational Data Mining (EDM) has emerged as a vital field of research, which harnesses the power of computational techniques to analyze educational data. With the increasing complexity and diversity of academic data, Deep Learning techniques have shown significant advantages in addressing the challenges associated with analyzing and modeling this data. Existing studies are scattered across various domains, making it challenging to gain a comprehensive understanding of how Deep Learning techniques can transform educational practices. This survey aims to systematically review the state-of-the-art in EDM with Deep Learning. We begin by providing a brief introduction to EDM and Deep Learning, highlighting their relevance in the context of modern education. Next, we present a detailed review of Deep Learning techniques applied in four typical educational scenarios, including knowledge tracing, student behavior detection, performance prediction, and personalized recommendation. Furthermore, a comprehensive overview of public datasets and processing tools for EDM is provided. Finally, we point out emerging trends and future directions, aiming to guide researchers and practitioners in advancing the field of EDM.

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.

Many platforms, such as e-commerce websites, offer both search and recommendation services simultaneously to better meet users' diverse needs. Recommendation services suggest items based on user preferences, while search services allow users to search for items before providing recommendations. Since users and items are often shared between the search and recommendation domains, there is a valuable opportunity to enhance the recommendation domain by leveraging user preferences extracted from the search domain. Existing approaches either overlook the shift in user intention between these domains or fail to capture the significant impact of learning from users' search queries on understanding their interests.

The sequential recommender (SR) system is a crucial component of modern recommender systems, as it aims to capture the evolving preferences of users. Significant efforts have been made to enhance the capabilities of SR systems. These methods typically follow the model-centric paradigm, which involves developing effective models based on fixed datasets. However, this approach often overlooks potential quality issues and flaws inherent in the data. Driven by the potential of data-centric AI, we propose a novel data-centric paradigm for developing an ideal training dataset using a model-agnostic dataset regeneration framework called DR4SR. This framework enables the regeneration of a dataset with exceptional cross-architecture generalizability. Additionally, we introduce the DR4SR+ framework, which incorporates a model-aware dataset personalizer to tailor the regenerated dataset specifically for a target model. To demonstrate the effectiveness of the data-centric paradigm, we integrate our framework with various model-centric methods and observe significant performance improvements across four widely adopted datasets. Furthermore, we conduct in-depth analyses to explore the potential of the data-centric paradigm and provide valuable insights. The code can be found at https://github.com/USTC-StarTeam/DR4SR.

Knowledge Graphs (KGs) enhance recommendations by providing external connectivity between items. However, there is limited research on distilling relevant knowledge in sequential recommendation, where item connections can change over time. To address this, we introduce the Temporal Knowledge Graph (TKG), which incorporates such dynamic features of user behaviors into the original KG while emphasizing sequential relationships. The TKG captures both patterns of entity dynamics (nodes) and structural dynamics (edges). Considering real-world applications with large-scale and rapidly evolving user behavior patterns, we propose an efficient two-phase framework called TKG-SRec, which strengthens Sequential Recommendation with Temporal KGs. In the first phase, we learn dynamic entity embeddings using our novel Knowledge Evolution Network (KEN) that brings together pretrained static knowledge with evolving temporal knowledge. In the second stage, downstream sequential recommender models utilize these time-specific dynamic entity embeddings with compatible neural backbones like GRUs, Transformers, and MLPs. From our extensive experiments over four datasets, TKG-SRec outperforms the current state-of-the-art by a statistically significant 5% on average. Detailed analysis validates that such filtered temporal knowledge better adapts entity embedding for sequential recommendation. In summary, TKG-SRec provides an effective and efficient approach.

In recommendation systems, users frequently engage in multiple types of behaviors, such as clicking, adding to cart, and purchasing. Multi-behavior sequential recommendation aims to jointly consider multiple behaviors to improve the target behavior's performance. However, with diversified behavior data, user behavior sequences will become very long in the short term, which brings challenges to the efficiency of the sequence recommendation model. Meanwhile, some behavior data will also bring inevitable noise to the modeling of user interests. To address the aforementioned issues, firstly, we develop the Efficient Behavior Sequence Miner (EBM) that efficiently captures intricate patterns in user behavior while maintaining low time complexity and parameter count. Secondly, we design hard and soft denoising modules for different noise types and fully explore the relationship between behaviors and noise. Finally, we introduce a contrastive loss function along with a guided training strategy to contrast the valid information with the noisy signal in the data, and seamlessly integrate the two denoising processes to achieve a high degree of decoupling of the noisy signal. Sufficient experiments on real-world datasets demonstrate the effectiveness and efficiency of our approach in dealing with multi-behavior sequential recommendation.

Click-Through Rate (CTR) prediction holds paramount significance in online advertising and recommendation scenarios. Despite the proliferation of recent CTR prediction models, the improvements in performance have remained limited, as evidenced by open-source benchmark assessments. Current researchers tend to focus on developing new models for various datasets and settings, often neglecting a crucial question: What is the key challenge that truly makes CTR prediction so demanding?

Accurately estimating packages’ arrival time in e-commerce can enhance users’ shopping experience and improve the placement rate of products. This problem is often formalized as an Origin-Destination (OD)-based ETA (i.e., estimated time of arrival) prediction task, where the delivery time is estimated mainly based on sender and receiver addresses and other context information. One inherent challenge of the OD-based ETA problem is that the delivery time highly depends on the actual delivery trajectory which is unknown at the time of prediction. In this article, we tackle this challenge by effectively exploiting historical delivery trajectories. We propose a novel Knowledge Distillation Graph neural network-based package ETA prediction (KDG-ETA) model, which uses knowledge distillation in the training phase to distill the knowledge of historical trajectories into OD pair embeddings. In KDG-ETA, a multi-level trajectory graph representation model is proposed to fully exploit trajectory information at the node-level, edge-level, and path-level. Then, the OD representations embedded with trajectory knowledge are combined with context embeddings from feature extraction module for delivery time prediction using an adaptive attention module. KDG-ETA consistently outperforms existing state-of-the-art OD-based ETA prediction methods on three real-world Alibaba datasets, reducing the Mean Absolute Error (MAE) by 3.0%–39.1% as demonstrated in our extensive empirical evaluation.

Sequential recommendation systems aim to exploit users’ sequential behavior patterns to capture their interaction intentions and improve recommendation accuracy. Existing sequential recommendation methods mainly focus on modeling the items’ chronological relationships in each individual user behavior sequence, which may not be effective in making accurate and robust recommendations. On the one hand, the performance of existing sequential recommendation methods is usually sensitive to the length of a user’s behavior sequence (i.e., the list of a user’s historically interacted items). On the other hand, besides the context information in each individual user behavior sequence, the collaborative information among different users’ behavior sequences is also crucial to make accurate recommendations. However, this kind of information is usually ignored by existing sequential recommendation methods. In this work, we propose a new sequential recommendation framework, which encodes the context information in each individual user behavior sequence as well as the collaborative information among the behavior sequences of different users, through building a local dependency graph for each item. We conduct extensive experiments to compare the proposed model with state-of-the-art sequential recommendation methods on five benchmark datasets. The experimental results demonstrate that the proposed model is able to achieve better recommendation performance than existing methods, by incorporating collaborative information.

CTR prediction is critical to industrial recommender systems. Recently, with the growth of business domains in enterprises, much attention has been focused on the multi-domain CTR recommendation. Numerous models have been proposed that attempt to use a unified model to serve multiple domains. Although much progress has been made, we argue that they ignore the importance of feature interactions and user behaviors when modeling cross-domain relations, which is a coarse-grained utilizing of domain information. To solve this problem, we propose Domain Facilitated Feature Modeling (DFFM) for CTR prediction. It incorporates domain-related information into the parameters of the feature interaction and user behavior modules, allowing for domain-specific learning of these two aspects. Extensive experiments are conducted on two public datasets and one industrial dataset to demonstrate the effectiveness of DFFM. We deploy the DFFM model in Huawei advertising platform and gain a 4.13% improvement of revenue on a two week online A/B test. Currently DFFM model has been used as the main traffic model, serving for hundreds of millions of people.

In sequential recommendation, multi-modal information (e.g., text or image) can provide a more comprehensive view of an item's profile. The optimal stage (early or late) to fuse modality features into item representations is still debated. We propose a graph-based approach (named MMSR) to fuse modality features in an adaptive order, enabling each modality to prioritize either its inherent sequential nature or its interplay with other modalities. MMSR represents each user's history as a graph, where the modality features of each item in a user's history sequence are denoted by cross-linked nodes. The edges between homogeneous nodes represent intra-modality sequential relationships, and the ones between heterogeneous nodes represent inter-modality interdependence relationships. During graph propagation, MMSR incorporates dual attention, differentiating homogeneous and heterogeneous neighbors. To adaptively assign nodes with distinct fusion orders, MMSR allows each node's representation to be asynchronously updated through an update gate. In scenarios where modalities exhibit stronger sequential relationships, the update gate prioritizes updates among homogeneous nodes. Conversely, when the interdependent relationships between modalities are more pronounced, the update gate prioritizes updates among heterogeneous nodes. Consequently, MMSR establishes a fusion order that spans a spectrum from early to late modality fusion. In experiments across six datasets, MMSR consistently outperforms state-of-the-art models, and our graph propagation methods surpass other graph neural networks. Additionally, MMSR naturally manages missing modalities. The code is available at: https://github.com/HoldenHu/MMSR.

The boom of generative models has paved the way for significant advances in recommender systems. For instance, pre-trained generative models offer unprecedented opportunities to improve recommender algorithms for user modeling. This workshop aims to provide a platform for researchers to actively explore and share innovative ideas on integrating generative models into recommender systems, mainly focusing on five key aspects: (i) enhancing recommender algorithms, (ii) generating personalized content in some scenarios such as micro-videos, (iii) changes in the user-system interaction paradigm, (iv) boosting trustworthiness checks, and (v) evaluation methodologies of generative recommendation. With the rapid development of generative models, a growing number of studies along the above directions are emerging, revealing the timeliness and necessity of this workshop. The related research will bring novel features to recommender systems and contribute to new tasks and technologies in both academia and industry. In the long run, this research direction might revolutionize the traditional recommender paradigm and lead to the maturation of next-generation recommender systems.

The sequential recommendation system has been widely studied for its promising effectiveness in capturing dynamic preferences buried in users' sequential behaviors. Despite the considerable achievements, existing methods usually focus on intra-sequence modeling while overlooking exploiting global collaborative information by inter-sequence modeling, resulting in inferior recommendation performance. Therefore, previous works attempt to tackle this problem with a global collaborative item graph constructed by pre-defined rules. However, these methods neglect two crucial properties when capturing global collaborative information, i.e., adaptiveness and personalization, yielding sub-optimal user representations. To this end, we propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR), that incorporates adaptive and personalized global collaborative information into sequential recommendation systems. Specifically, we first learn an adaptive global graph among all items and capture global collaborative information with it in a self-supervised fashion, whose computational burden can be further alleviated by the proposed SVD-based accelerator. Furthermore, based on the graph, we propose to extract and utilize personalized item correlations in the form of relative positional encoding, which is a highly compatible manner of personalizing the utilization of global collaborative information. Finally, the entire framework is optimized in a multi-task learning paradigm, thus each part of APGL4SR can be mutually reinforced. As a generic framework, APGL4SR can not only outperform other baselines with significant margins, but also exhibit promising versatility, the ability to learn a meaningful global collaborative graph, and the ability to alleviate the dimensional collapse issue of item embeddings.

E-commerce live streaming as an increasingly popular sales model has generated a significant amount of gross merchandise value (GMV) for e-commerce platforms. Live streaming recommendation systems (LSRS) of e-commerce aim to recommend the most appropriate live channels for users to motivate them to buy products. Existing LSRS methods focus only on the user’s interaction behaviors on the live channel (live domain) while ignoring the user’s behaviors and intentions on the e-commerce product (product domain). As a result, the user’s consistent purchase intentions in the cross-domain are not being fully captured, especially when user present differentiated purchase intentions in the cross-domain. How to disentangle user’s consistent intentions and domain-specific intentions in the cross-domain poses a challenge to the LSRS of e-commerce platforms. In this paper, we present a live channel recommendation method, named eLiveRec, developed for Taobao, one of the largest e-commerce platform in the world. Specifically, eLiveRec employs the disentangled encoder module to learn user’s cross-domain consistent intentions and domain-specific intentions. Then, an adaptive multi-task learning framework is developed to jointly optimize the multiple objectives (e.g., stay time, click goods bag, and click products after entering channel) related to live streaming recommendation. In this way, the performance of live streaming recommendation can be further improved and con-form to standard industry RS paradigms. Extensive experiments are conducted on a large-scale industry dataset collected from Taobao Live platform have been performed. Both online and offline experimental results indicate that eLiveRec consistently outperforms existing state-of-the-art baseline methods.

Predicting Estimated Time of Arrival (ETA) for packages is a critical problem in e-commerce. The prediction is often made based on spatial (sending and receiving addresses), temporal (payment time), and context (merchants) attributes. Existing methods usually formalize this task as an Origin-Destination (OD) ETA prediction problem and exploit the attribute relations with graph learning. However, most existing methods make use of fixed and manually defined graph structures, which are often not optimal for downstream ETA task and hence lead to unsatisfactory prediction results. In addition, current ETA models tend to focus on prediction accuracy without considering fulfillment rate. This may lead to a low fulfillment rate in practice, i.e., actual delivery time is much longer than estimations provided by models, which consequently exacerbates the frustrating experiences for users. To address these issues, we propose a novel Graph Structure Learning-based Quantile Regression (GSL-QR) model for e-commerce ETA prediction in this paper. Specifically, we utilize graph structure learning to dynamically update the spatial and temporal relation graphs of orders and learn optimal graph structures and graph embeddings guided by downstream ETA prediction task. To guarantee both prediction accuracy and order fulfillment rate, we design a multi-objective quantile regression in GSL-QR that can find the Pareto solution of the problem. In order to extend GSL to large-scale real-world graphs, we devise a Fast Sampling-based Graph Structure Learning (FS-GSL) method, which can significantly reduce the computational complexity of graph structure learning. Finally, we conduct comprehensive experiments on three industrial datasets collected from Alibaba e-commerce platform. The results demonstrate that the proposed model can significantly outperform baselines on both ETA prediction accuracy and order fulfillment rate.

Recommendation models utilizing Graph Convolutional Networks (GCNs) have achieved state-of-the-art performance, as they can integrate both the node information and the topological structure of the user-item interaction graph. However, these GCN-based recommendation models not only suffer from over-smoothing when stacking too many layers but also bear performance degeneration resulting from the existence of noise in user-item interactions. In this paper, we first identify a recommendation dilemma of over-smoothing and solution collapsing in current GCN-based models. Specifically, these models usually aggregate all layer embeddings for node updating and achieve their best recommendation performance within a few layers because of over-smoothing. Conversely, if we place learnable weights on layer embeddings for node updating, the weight space will always collapse to a fixed point, at which the weighting of the ego layer almost holds all. We propose a layer-refined GCN model, dubbed LayerGCN, that refines layer representations during information propagation and node updating of GCN. Moreover, previous GCN-based recommendation models aggregate all incoming information from neighbors without distinguishing the noise nodes, which deteriorates the recommendation performance. Our model further prunes the edges of the user-item interaction graph following a degree-sensitive probability instead of the uniform distribution. Experimental results show that the proposed model outperforms the state-of-the-art models significantly on four public datasets with fast training convergence. The implementation code of the proposed method is available at https://github.com/enoche/ImRec.

The RecSys 2023 Challenge involved a conversion prediction task in the online advertising space. The dataset was provided by ShareChat (Mohalla Tech Pvt Ltd). The challenge data represents a sample of ad impressions served to the users over a period of 22 days and the task is for a given ad impression, to predict a conversion (install an app) will happen or not. The challenge ran for 3 months with a public dashboard. There were 519 teams registered and 231 teams made at least one submission. The task setting represents an important research area of modeling ad recommendations under user privacy. We identify interesting themes in feature engineering, addressing sparsity and calibrating across multi-step predictions.

User Behavior Modeling (UBM) plays a critical role in user interest learning, and has been extensively used in recommender systems. The exploration of key interactive patterns between users and items has yielded significant improvements and great commercial success across a variety of recommendation tasks. This tutorial aims to offer an in-depth exploration of this evolving research topic. We start by reviewing the research background of UBM, paving the way to a clearer understanding of the opportunities and challenges. Then, we present a systematic categorization of existing UBM research works, which can be categorized into four different directions including Conventional UBM, Long-Sequence UBM, Multi-Type UBM, and UBM with Side Information. To provide an expansive understanding, we delve into each category, discussing representative models while highlighting their respective strengths and weaknesses. Furthermore, we elucidate on the industrial applications of UBM methods, aiming to provide insights into the practical value of existing UBM solutions. Finally, we identify some open challenges and future prospects in UBM. This comprehensive tutorial serves to provide a solid foundation for anyone looking to understand and implement UBM in their research or business.

Interactive recommender systems have attracted increasingly research attentions from both academia and industry. This workshop is a half-day event, which provides a forum for researchers and practitioners to discuss recent research progress and novel research directions about interactive recommender systems. The program will include two keynotes and 6 to 8 research paper presentations. The objective of this workshop is to consolidate the recent technical progresses about interactive recommendation, which will be a promising research and development direction for future recommendation technologies. This workshop will attract the attention of researchers from both academia and industry. It aligns with WSDM's spirit of promoting the collaborations between academia and industry.

Recommender systems have become increasingly important in our daily lives since they play an important role in mitigating the information overload problem, especially in many user-oriented online services. Recommender systems aim to identify a set of items that best match users' explicit or implicit preferences, by utilizing the user and item interactions to improve the accuracy. With the fast advancement of deep neural networks (DNNs) in the past few decades, recommendation techniques have achieved promising performance. However, we still meet three inherent challenges to design deep recommender systems (DRS): 1) the majority of existing DRS are developed based on hand-crafted components, which requires ample expert knowledge recommender systems; 2) human error and bias can lead to suboptimal components, which reduces the recommendation effectiveness; 3) non-trivial time and engineering efforts are usually required to design the task-specific components in different recommendation scenarios.

Providing accurate estimated time of package delivery on users' purchasing pages for e-commerce platforms is of great importance to their purchasing decisions and post-purchase experiences. Although this problem shares some common issues with the conventional estimated time of arrival (ETA), it is more challenging with the following aspects: 1) Inductive inference. Models are required to predict ETA for orders with unseen retailers and addresses; 2) High-order interaction of order semantic information. Apart from the spatio-temporal features, the estimated time also varies greatly with other factors, such as the packaging efficiency of retailers, as well as the high-order interaction of these factors. In this paper, we propose an inductive graph transformer (IGT) that leverages raw feature information and structural graph data to estimate package delivery time. Different from previous graph transformer architectures, IGT adopts a decoupled pipeline and trains transformer as a regression function that can capture the multiplex information from both raw feature and dense embeddings encoded by a graph neural network (GNN). In addition, we further simplify the GNN structure by removing its non-linear activation and the learnable linear transformation matrix. The reduced parameter search space and linear information propagation in the simplified GNN enable the IGT to be applied in large-scale industrial scenarios. Experiments on real-world logistics datasets show that our proposed model can significantly outperform the state-of-the-art methods on estimation of delivery time.

This paper studies the multi-modal recommendation problem, where the item multi-modality information (e.g., images and textual descriptions) is exploited to improve the recommendation accuracy. Besides the user-item interaction graph, existing state-of-the-art methods usually use auxiliary graphs (e.g., user-user or item-item relation graph) to augment the learned representations of users and/or items. These representations are often propagated and aggregated on auxiliary graphs using graph convolutional networks, which can be prohibitively expensive in computation and memory, especially for large graphs. Moreover, existing multi-modal recommendation methods usually leverage randomly sampled negative examples in Bayesian Personalized Ranking (BPR) loss to guide the learning of user/item representations, which increases the computational cost on large graphs and may also bring noisy supervision signals into the training process. To tackle the above issues, we propose a novel self-supervised multi-modal recommendation model, dubbed BM3, which requires neither augmentations from auxiliary graphs nor negative samples. Specifically, BM3 first bootstraps latent contrastive views from the representations of users and items with a simple dropout augmentation. It then jointly optimizes three multi-modal objectives to learn the representations of users and items by reconstructing the user-item interaction graph and aligning modality features under both inter- and intra-modality perspectives. BM3 alleviates both the need for contrasting with negative examples and the complex graph augmentation from an additional target network for contrastive view generation. We show BM3 outperforms prior recommendation models on three datasets with number of nodes ranging from 20K to 200K, while achieving a 2-9 × reduction in training time. Code implementation is located at: https://github.com/enoche/BM3.

Explainable recommendation systems provide explanations for recommendation results to improve their transparency and persuasiveness. The existing explainable recommendation methods generate textual explanations without explicitly considering the user's preferences on different aspects of the item. In this paper, we propose a novel explanation generation framework, namelyAspect-guidedExplanation generation withSyntaxGraph (AESG), for explainable recommendation. Specifically, AESG employs a review-based syntax graph to provide a unified view of the user/item details. An aspect-guided graph pooling operator is proposed to extract the aspect-relevant information from the review-based syntax graphs to model the user's preferences on an item at the aspect level. Then, an aspect-guided explanation decoder is developed to generate aspects and aspect-relevant explanations based on the attention mechanism. The experimental results on three real datasets indicate that AESG outperforms state-of-the-art explanation generation methods in both single-aspect and multi-aspect explanation generation tasks, and also achieves comparable or even better preference prediction accuracy than strong baseline methods.

Graph neural networks (GNNs) have witnessed widespread adoption due to their ability to learn superior representations for graph data. While GNNs exhibit strong discriminative power, they often fall short of learning the underlying node distribution for increased robustness. To deal with this, inspired by generative adversarial networks (GANs), we investigate the problem of adversarial learning on graph neural networks, and propose a novel framework named NAGNN (i.e., Neighbor-anchoring Adversarial Graph Neural Networks) for graph representation learning, which trains not only a discriminator but also a generator that compete with each other. In particular, we propose a novel neighbor-anchoring strategy, where the generator produces samples with explicit features and neighborhood structures anchored on a reference real node, so that the discriminator can perform neighborhood aggregation on the fake samples to learn superior representation. The advantage of our neighbor-anchoring strategy can be demonstrated both theoretically and empirically. Furthermore, as a by-product, our generator can synthesize realistic-looking features, enabling potential applications such as automatic content summarization. Finally, we conduct extensive experiments on four public benchmark datasets, and achieve promising results under both quantitative and qualitative evaluations.

Graph neural networks (GNN) have recently been applied to exploit knowledge graph (KG) for recommendation. Existing GNN-based methods explicitly model the dependency between an entity and its local graph context in KG (i.e., the set of its first-order neighbors), but may not be effective in capturing its non-local graph context (i.e., the set of most related high-order neighbors). In this paper, we propose a novel recommendation framework, named Contextualized Graph Attention Network (CGAT), which can explicitly exploit both local and non-local graph context information of an entity in KG. More specifically, CGAT captures the local context information by a user-specific graph attention mechanism, considering a user's personalized preferences on entities. In addition, CGAT employs a biased random walk sampling process to extract the non-local context of an entity, and utilizes a Recurrent Neural Network (RNN) to model the dependency between the entity and its non-local contextual entities. To capture the user's personalized preferences on items, an item-specific attention mechanism is also developed to model the dependency between a target item and the contextual items extracted from the user's historical behaviors. We compared CGAT with state-of-the-art KG-based recommendation methods on real datasets, and the experimental results demonstrate the effectiveness of CGAT.

The user review data have been demonstrated to be effective in solving different recommendation problems. Previous review-based recommendation methods usually employ sophisticated compositional models, such as Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), to learn semantic representations from the review data for recommendation. However, these methods mainly capture the local dependency between neighboring words in a word window, and they treat each review equally. Therefore, they may not be effective in capturing the global dependency between words and tend to be easily biased by noise review information. In this paper, we propose a novel review-based recommendation model, named Review Graph Neural Network (RGNN). Specifically, RGNN builds a specific review graph for each individual user/item, which provides a global view about the user/item properties to help weaken the biases caused by noise review information. A type-aware graph attention mechanism is developed to learn semantic embeddings of words. Moreover, a personalized graph pooling operator is proposed to learn hierarchical representations of the review graph to form the semantic representation for each user/item. We compared RGNN with state-of-the-art review-based recommendation approaches on two real-world datasets. The experimental results indicate that RGNN consistently outperforms baseline methods, in terms of Mean Square Error (MSE).

Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions. Existing CF-based methods commonly adopt negative sampling to discriminate different items. That is, observed user-item pairs are treated as positive instances; unobserved pairs are considered as negative instances and are sampled under a defined distribution for training. Training with negative sampling on large datasets is computationally expensive. Further, negative items should be carefully sampled under the defined distribution, in order to avoid selecting an observed positive item in the training dataset. Unavoidably, some negative items sampled from the training dataset could be positive in the test set. Recently, self-supervised learning (SSL) , has emerged as a powerful tool to learn a model without negative samples. In this paper, we propose a self-supervised collaborative filtering framework (SelfCF) , that is specially designed for recommender scenario with implicit feedback. The proposed SelfCF framework simplifies Siamese networks and can be easily applied to existing deep-learning based CF models, which we refer to as backbone networks. The main idea of SelfCF is to augment the latent embeddings generated by backbone networks instead of the raw input of user/item ids. We propose and study three embedding perturbation techniques that can be applied to different types of backbone networks including both traditional CF models and graph-based models. The framework enables learning informative representations of users and items without negative samples, and is agnostic to the encapsulated backbones. We conduct experimental comparisons on four datasets, one self-supervised framework, and eight baselines to show that our framework may achieve even better recommendation accuracy than the encapsulated supervised counterpart with a 2×–4× faster training speed. The results also demonstrate that SelfCF can boost up the accuracy of a self-supervised framework BUIR by 17.79% on average and shows competitive performance with baselines.

The goal of sequential recommendation is to predict the next item that a user would like to interact with, by capturing her dynamic historical behaviors. However, most existing sequential recommendation methods do not focus on solving the long-tail item recommendation problem that is caused by the imbalanced distribution of item data. To solve this problem, we propose a novel sequential recommendation framework, named MASR (ie Memory Bank Augmented Long-tail Sequential Recommendation). MASR is an "Open-book'' model that combines novel types of memory banks and a retriever-copy network to alleviate the long-tail problem. During inference, the designed retriever-copy network retrieves related sequences from the training samples and copies the useful information as a cue to improve the recommendation performance on tail items. Two designed memory banks provide reference samples to the retriever-copy network by memorizing the historical samples appearing in the training phase. Extensive experiments have been performed on five real-world datasets to demonstrate the effectiveness of the proposed MASR model. The experimental results indicate that MASR consistently outperforms baseline methods in terms of recommendation performance on tail items.

Although many algorithms have been presented to tackle the curse of dimensionality in high-dimensional clustering, most of these algorithms require prior knowledge of the number of clusters. Besides, these existing algorithms create only a hard or fuzzy partition for high-dimensional objects, which are often located in highly overlapping areas. The adoption of hard/fuzzy partition ignores the ambiguity in the assignment of objects and may lead to performance degradation. To address these issues, we propose a novel self-reconstructive evidential clustering (SREC) algorithm. After learning the correlations between objects from a self-reconstruction process, SREC provides a human-readable chart. Through this chart, users can select several objects existing in the dataset as the cluster centers, instead of just detecting the number of clusters. Under the framework of evidence theory, SREC derives a more flexible credal partition that improves the fault tolerance of clustering. Ablation study demonstrates the benefits of the self-reconstruction and evidence theory. Comparison experiments on real-world datasets show that SREC consumes competitive running time and performs better than other state-of-the-art algorithms. We also apply SREC in a real-world application scenario to illustrate the rationality of selecting cluster centers by human intervention.

The performance of$K$-nearest neighbor (K-NN) classification depends significantly on the searched neighborhoods of test samples, namely, the neighborhood size$K$and the used distance metric. For the two issues, many methods either to acquire the adaptive$K$or to learn a variant metric have been presented and yielded appropriate performance. However, most of the existing methods ignore the fact that these two factors can be jointly learned. Besides, nearly all the metric learning methods aim to shrink intra-class distance while expanding inter-class distance. In this way, embedding the learned metric directly into the K-NN does not efficiently improve its accuracy. To address these issues, we propose a joint K-NN algorithm with the help of evidence theory, optimizing the joint learning of adaptive$K$and distance matrix based on the feedback from error function. Ablation study demonstrates the performance improvement from the joint learning, and comparison experiments on real-world datasets show that our approach consumes competitive running time and achieves better performance than other state-of-the-art algorithms.

While graph neural networks (GNNs) exhibit strong discriminative power, they often fall short of learning the underlying node distribution for increased robustness. To deal with this, inspired by generative adversarial networks (GANs), we investigate the problem of adversarial learning on graph neural networks, and propose a novel framework named NAGNN (i.e., Neighbor-anchoring Adversarial Graph Neural Networks) for graph representation learning, which trains not only a discriminator but also a generator that compete with each other. In particular, we propose a novel neighbor-anchoring strategy, where the generator produces samples with explicit features and neighborhood structures anchored on a reference real node, so that the discriminator can perform neighborhood aggregation on the fake samples to learn superior representations.

Next Point-of Interest (POI) recommendation plays an important role in location-based applications, which aims to recommend the next POIs to users that they are most likely to visit based on their historical trajectories. Existing methods usually use rich side information, or customized POI graphs to capture the sequential patterns among POIs. However, the graphs only focus on connectivity between POIs. Few studies propose to explicitly learn a weighted POI graph, which could reflect the transition patterns among POIs and show the importance of its different neighbors for each POI. In addition, these approaches simply utilize the user characteristics for personalized POI recommendation without sufficient consideration. To this end, we construct a novel User-POI Knowledge Graph with strong representation ability, called Spatial-Temporal Knowledge Graph (STKG). STKG is used to learn the representations of each node (i.e., user, POI) and each edge. Then, we design a similarity function to construct our POI transition graph based on the learned representations. To incorporate the learned graph into sequential model, we propose a novel network Graph-Flashback for recommendation. Graph-Flashback applies a simplified Graph Convolution Network (GCN) on the POI transition graph to enrich the representation of each POI. Further, we define a similarity function to consider both spatiotemporal information and user preference in modelling sequential regularity. Experimental results on two real-world datasets show that our proposed method achieves the state-of-the-art performance and significantly outperforms all existing solutions.

Estimated Time of package Arrival (ETA) is an essential task for Alibaba E-commerce platforms like Taobao and Tmall, which may influence the user experiences of one billion customers. The main challenge in ETA prediction of Alibaba platforms is learning from high-dimensional categorical attributes, which is equally important to obtain appropriate representations for each feature, and describe the proximity among them. Although recent supervised end-to-end methods have achieved great improvements, the unsupervised embedding method for categorical attributes has not been well-studied yet, especially when dealing with large-scale sparse datasets.

Counterfactual explanations are minimum changes of a given input to alter the original prediction by a machine learning model, usually from an undesirable prediction to a desirable one. Previous works frame this problem as a constrained cost minimization, where the cost is defined as L1/L2 distance (or variants) over multiple features to measure the change. In real-life applications, features of different types are hardly comparable and it is difficult to measure the changes of heterogeneous features by a single cost function. Moreover, existing approaches do not support interactive exploration of counterfactual explanations. To address above issues, we propose the skyline counterfactual explanations that define the skyline of counterfactual explanations as all non-dominated changes. We solve this problem as multi-objective optimization over actionable features. This approach does not require any cost function over heterogeneous features. With the skyline, the user can interactively and incrementally refine their goals on the features and magnitudes to be changed, especially when lacking prior knowledge to express their needs precisely. Intensive experiment results on three real-life datasets demonstrate that the skyline method provides a friendly way for finding interesting counterfactual explanations, and achieves superior results compared to the state-of-the-art methods.

The micro-video recommendation system becomes an essential part of the e-commerce platform, which helps disseminate micro-videos to potentially interested users. Existing micro-video recommendation methods only focus on users' browsing behaviors on micro-videos, but ignore their purchasing intentions in the e-commerce environment. Thus, they usually achieve unsatisfied e-commerce micro-video recommendation performances. To address this problem, we design a sequential multi-modal information transfer network (SEMI), which utilizes product-domain user behaviors to assist micro-video recommendations. SEMI effectively selects relevant items (i.e., micro-videos and products) with multi-modal features in the micro-video domain and product domain to characterize users' preferences. Moreover, we also propose a cross-domain contrastive learning (CCL) algorithm to pre-train sequence encoders for modeling users' sequential behaviors in these two domains. The objective of CCL is to maximize a lower bound of the mutual information between different domains. We have performed extensive experiments on a large-scale dataset collected from Taobao, a world-leading e-commerce platform. Experimental results show that the proposed method achieves significant improvements over state-of-the-art recommendation methods. Moreover, the proposed method has also been deployed on Taobao, and the online A/B testing results further demonstrate its practical value.

Proper initialization is crucial to the optimization and the generalization of neural networks. However, most existing neural recommendation systems initialize the user and item embeddings randomly. In this work, we propose a new initialization scheme for user and item embeddings called Laplacian Eigenmaps with Popularity-based Regularization for Isolated Data (LEPORID). LEPORID endows the embeddings with information regarding multi-scale neighborhood structures on the data manifold and performs adaptive regularization to compensate for high embedding variance on the tail of the data distribution. Exploiting matrix sparsity, LEPORID embeddings can be computed efficiently. We evaluate LEPORID in a wide range of neural recommendation models. In contrast to the recent surprising finding that the simple K-nearest-neighbor (KNN) method often outperforms neural recommendation systems, we show that existing neural systems initialized with LEPORID often perform on par or better than KNN. To maximize the effects of the initialization, we propose the Dual-Loss Residual Recommendation (DLR^2) network, which, when initialized with LEPORID, substantially outperforms both traditional and state-of-the-art neural recommender systems.

Discovering disease-gene association is a fundamental and critical biomedical task, which assists biologists and physicians to discover pathogenic mechanism of syndromes. With various clinical biomarkers measuring the similarities among genes and disease phenotypes, network-based semi-supervised learning (NSSL) has been commonly utilized by these studies to address this class-imbalanced large-scale data issue. However, most existing NSSL approaches are based on linear models and suffer from two major limitations: 1) They implicitly consider a local-structure representation for each candidate; 2) They are unable to capture nonlinear associations between diseases and genes. In this paper, we propose a new framework for disease-gene association task by combining Graph Convolutional Network (GCN) and matrix factorization, named GCN-MF. With the help of GCN, we could capture non-linear interactions and exploit measured similarities. Moreover, we define a margin control loss function to reduce the effect of sparsity. Empirical results demonstrate that the proposed deep learning algorithm outperforms all other state-of-the-art methods on most of metrics.

This paper aims at improvement on the effectiveness of matrix decomposition (MD) methods for implicit feedback. We highlight two critical limitations of existing works. First, due to the large number of unlabeled feedback, most existing works employ a uniform weight to the missing data to reduce computational complexity. However, such a uniform assumption may rarely hold in real-world scenarios. Second, the commonly-used bilateral loss function might be infinite if the data point is mis-classified. Outliers may have such issues and misguide the learning process. We address the above two issues by learning a robust asymmetric learning model. By leveraging the cost-sensitive learning and capped unilateral loss function, our robust MD objective function integrates them into a joint formulation, where the low-rank basis for user/item profiles can be modeled in an effective and robust way. Particularly, a novel log-determinant function is employed to refine the nuclear norm with respect to the low-rank approximation. We derive an iterative re-weighted algorithm to efficiently minimize this MD objective, and also rigorously prove a lower error bound of the proposed algorithm compared to the 1-bit matrix completion method. Finally, we show the promising experimental results of our algorithm on benchmark recommendation datasets.

Geographical characteristics derived from the historical check-in data have been reported effective in improving location recommendation accuracy. However, previous studies mainly exploit geographical characteristics from a user's perspective, via modeling the geographical distribution of each individual user's check-ins. In this paper, we are interested in exploiting geographical characteristics from a location perspective, by modeling the geographical neighborhood of a location. The neighborhood is modeled at two levels: the instance-level neighborhood defined by a few nearest neighbors of the location, and the region-level neighborhood for the geographical region where the location exists. We propose a novel recommendation approach, namely Instance-Region Neighborhood Matrix Factorization (IRenMF), which exploits two levels of geographical neighborhood characteristics: a) instance-level characteristics, i.e., nearest neighboring locations tend to share more similar user preferences; and b) region-level characteristics, i.e., locations in the same geographical region may share similar user preferences. In IRenMF, the two levels of geographical characteristics are naturally incorporated into the learning of latent features of users and locations, so that IRenMF predicts users' preferences on locations more accurately. Extensive experiments on the real data collected from Gowalla, a popular LBSN, demonstrate the effectiveness and advantages of our approach.

Rating prediction is to predict the preference rating of a user to an item that she has not rated before. Using the business review data from Yelp, in this paper, we study business rating prediction. A business here can be a restaurant, a shopping mall or other kind of businesses. Different from most other types of items that have been studied in various recommender systems (e.g., movie, song, book), a business physically exists at a geographical location, and most businesses have geographical neighbors within walking distance. When a user visits a business, there is a good chance that she walks by its neighbors. Through data analysis, we observe that there exists weak positive correlation between a business's ratings and its neighbors' ratings, regardless of the categories of businesses. Based on this observation, we assume that a user's rating to a business is determined by both the intrinsic characteristics of the business and the extrinsic characteristics of its geographical neighbors. Using the widely adopted latent factor model for rating prediction, in our proposed solution, we use two kinds of latent factors to model a business: one for its intrinsic characteristics and the other for its extrinsic characteristics. The latter encodes the neighborhood influence of this business to its geographical neighbors. In our experiments, we show that by incorporating geographical neighborhood influences, much lower prediction error is achieved than the state-of-the-art models including Biased MF, SVD++, and Social MF. The prediction error is further reduced by incorporating influences from business category and review content.

Location-based social networks (LBSNs) offer researchers rich data to study people's online activities and mobility patterns. One important application of such studies is to provide personalized point-of-interest (POI) recommendations to enhance user experience in LBSNs. Previous solutions directly predict users' preference on locations but fail to provide insights about users' preference transitions among locations. In this work, we propose a novel category-aware POI recommendation model, which exploits the transition patterns of users' preference over location categories to improve location recommendation accuracy. Our approach consists of two stages: (1) preference transition (over location categories) prediction, and (2) category-aware POI recommendation. Matrix factorization is employed to predict a user's preference transitions over categories and then her preference on locations in the corresponding categories. Real data based experiments demonstrate that our approach outperforms the state-of-the-art POI recommendation models by at least 39.75% in terms of recall.