Short videos have gained immense popularity, necessitating effective recommender systems that cater to individual preferences. The platforms use advanced algorithms to analyze user engagement and provide videos that satisfy users. A critical factor in user satisfaction is immersion , defined as the feeling of being deeply engaged in an activity. However, existing recommendation algorithms in the short video scenario have largely disregarded user immersion. Our study integrates user immersion into recommendation systems, aiming to predict immersion from user interactions and recommend items to enhance the overall viewing experience. Based on the user study of collecting and analyzing user immersion, we integrate immersion into the recommendations for both lab and large-scale scenarios. We adapt user-annotated immersion to large-scale real-world datasets without immersion labels. Specifically, we propose ImmersRec , an immersion-aware recommendation framework with immersion prediction fine-tuning, immersion knowledge alignment, and immersion-enhanced recommendation. Extensive experiments on two short video platforms indicate that our approach achieves significant enhancements among various context-aware recommender backbones. We investigate the predicted immersion and find it impacts not only short-term utility but also long-term user engagement. This research pioneers the incorporation of user immersion in short video recommendation algorithms, emphasizing its potential for improving recommendations with minimal data. The code can be available at https://github.com/hezy18/ImmersRec .

Recommendation model interpretation aims to reveal the relationships between inputs, model internal representations, and outputs to enhance the transparency, interpretability, and trustworthiness of recommendation systems. However, the inherent complexity and opacity of deep learning models pose challenges for model-level interpretation. Moreover, most existing methods for interpreting recommendation models are tailored to specific architectures or model types, limiting their generalizability across different types of recommenders. In this article, we propose RecSAE, a generalizable probing framework that interprets Rec ommendation models with S parse A uto E ncoders. The framework extracts interpretable latents from the internal representations of recommendation models and links them to semantic concepts for interpretations. It does not alter original models during interpretations and also enables targeted tuning to models. Experiments on three types of recommendation models (general, graph-based, sequential) with four widely used public datasets demonstrate the effectiveness and generalization of the RecSAE framework. The interpreted concepts are further validated by human experts, showing strong alignment with human perception. Overall, RecSAE serves as a novel step in both model-level interpretations to various types of recommendation models without affecting their functions and offering potential for targeted tuning of models. The code and data are available at https://github.com/Alice1998/RecSAE .

Despite their powerful text generation capabilities, large language models (LLMs) still struggle to effectively utilize external tools to solve complex tasks, a challenge known as tool learning. Existing methods primarily rely on supervised fine-tuning, treating tool learning as a text generation problem while overlooking the decision-making complexities inherent in multi-step contexts. In this work, we propose modeling tool learning as a dynamic decision-making process and introduce StepTool, a novel step-grained reinforcement learning framework that enhances LLMs' capabilities in multi-step tool use. StepTool comprises two key components: Step-grained Reward Shaping, which assigns rewards to each tool interaction based on its invocation success and contribution to task completion; and Step-grained Optimization, which applies policy gradient methods to optimize the model across multiple decision steps. Extensive experiments across diverse benchmarks show that StepTool consistently outperforms both SFT-based and RL-based baselines in terms of task Pass Rate and Recall of relevant tools. Furthermore, our analysis suggests that StepTool helps models discover new tool-use strategies rather than merely re-weighting prior knowledge. These results highlight the importance of fine-grained decision modeling in tool learning and establish StepTool as a general and robust solution for enhancing multi-step tool use in LLMs. Code and data are available at https://github.com/yuyq18/StepTool.

Click-Through Rate (CTR) prediction is a fundamental task in online advertising and recommender systems, requiring the effective modeling of feature interactions. While existing methods have improved overall prediction performance, the performance of long-tail users with limited historical data remains suboptimal. These users face two primary challenges: (i) insufficient training data leading to inaccurate predictions, and (ii) an imbalanced sample distribution that biases model learning toward head users. To address these challenges, we propose a novel framework that enhances long-tail user performance through hierarchical distribution alignment, hierarchical residual learning, and adaptive distrbution calibration. Our method first captures the shared patterns between head and long-tail users via hierarchical distribution alignment, then learns group-specific information through hierarchical residual learning. Additionally, we re-balance the sample distributions of head users and long-tail users by dynamic reweighting. To counteract potential biases introduced by reweighting, we further incorporate a distribution calibration module. Our method is model-agnostic and can be seamlessly integrated into various CTR prediction architectures that rely on feature interactions. Extensive experiments on public datasets and an online experiment demonstrate that our approach significantly improves accuracy and fairness for long-tail users while maintaining similar or even better overall performance.

Instant messaging with texts and stickers has become a widely adopted communication medium, enabling efficient expression of user semantics and emotions. With the increased use of stickers conveying information and feelings, sticker retrieval and recommendation has emerged as an important area of research. However, a major limitation in existing literature has been the lack of datasets capturing temporal and user-specific sticker interactions, which has hindered further progress in user modeling and sticker personalization. To address this, we introduce User-Sticker, a dataset that includes temporal and user anonymous ID across conversations. It is the largest publicly available sticker dataset to date, containing 22K unique users, 370K stickers, and 8.3M messages. The raw data was collected from a popular messaging platform from 67 conversations over 720 hours of crawling. All text and image data were carefully vetted for safety and privacy checks and modifications. Spanning 10 domains, the U-Sticker dataset captures rich temporal, multilingual, and cross-domain behaviors not previously available in other datasets. Extensive quantitative and qualitative experiments demonstrate U-Sticker's practical applications in user behavior modeling and personalized recommendation and highlight its potential to further research areas in personalized retrieval and conversational studies. U-Sticker dataset is publicly available.

The rapid growth of short videos has necessitated effective recommender systems to match users with content tailored to their evolving preferences. Current video recommendation models primarily treat each video as a whole, overlooking the dynamic nature of user preferences with specific video segments. In contrast, our research focuses on segment-level user interest modeling, which is crucial for understanding how users' preferences evolve during video browsing. To capture users' dynamic segment interests, we propose an innovative model that integrates a hybrid representation module, a multi-modal user-video encoder, and a segment interest decoder. Our model addresses the challenges of capturing dynamic interest patterns, missing segment-level labels, and fusing different modalities, achieving precise segment-level interest prediction.

Cross-domain recommendation (CDR) has emerged as a promising direction for expanding the applicability of recommendation systems. Recent advances in CDR have demonstrated the effectiveness of the unified distribution paradigm, which leverages shared distributions to transfer knowledge across domains and employs domain-specific adapters for targeted recommendations. While this well-designed paradigm shows promising performance, existing methods require extra supervision signals (e.g. contrastive learning on domain-masked embeddings) to maintain unified distributions across domains, leading to an inherent trade-off between unified objectives and domain-specific preference modeling. To address these limitations, we propose CD-CDR (Conditional Diffusion-CDR), a novel approach that leverages a shared conditional diffusion model to learn unified item distributions and facilitate knowledge transfer across domains. The key insight is to utilize the powerful generative capabilities of diffusion models to learn a shared distribution while naturally incorporating domain-specific characteristics through conditional generation. This design enables CD-CDR to replace traditional adapters with generation conditions as an integral part of the distribution model, thereby eliminating extra supervision signals and fundamentally resolving the trade-off between unified and domain-specific objectives. Extensive experiments on six domain pairs from two real-world datasets demonstrate that CD-CDR significantly outperforms existing methods for both normal and cold-start settings. To the best of our knowledge, this is the first work to explore the unified distribution paradigm in CDR using conditional diffusion models.

With the development of multi-modal modeling techniques, recent sequential recommender systems enhance transferability by incorporating cross-domain universal multi-modal data, e.g., text and image. Existing methods typically adopt pairwise alignment to alleviate the gap between modalities. However, this alignment paradigm has limitations on explainability, consistency, and expansibility, resulting in suboptimal performance. This paper proposes a novel Explainable multi-modality Alignment method for transferable Rec ommender systems, i.e., EARec. Specifically, we design a two-stage framework to achieve explainable modality alignment in the source domain and recommendation based on aligned modality representations in the target domain. In the first stage, we adopt a generative task to align various modalities in parallel to a shared anchor with explainable meaning. All modalities share the same anchor to ensure consistent direction. Additionally, we treat behavior as an independent modality to integrate task-specific information into the alignment framework. In the second stage, we compose multiple item modality representation models trained in the first stage to obtain a unified model capable of understanding various modalities simultaneously, thereby providing high-quality item modality representations for recommendations in the target domain. Benefiting from the approach of parallel modality alignment followed by model composition, the framework shows flexibility in expanding new modalities. Experimental results on multiple public datasets demonstrate the superiority of EARec over baselines, and further analyses indicate the explainability and expansibility of the proposed alignment method.

Instant Messaging is a popular mean for daily communication, allowing users to send text and stickers.As the saying goes, "a picture is worth a thousand words", so developing an effective sticker retrieval technique is crucial for enhancing user experience.However, existing sticker retrieval methods rely on labeled data to interpret stickers, and general-purpose Vision-Language Models (VLMs) often struggle to capture the unique semantics of stickers.Additionally, relevance-based sticker retrieval methods lack personalization, creating a gap between diverse user expectations and retrieval results.To address these, we propose the Personalized Sticker Retrieval with Vision-Language Model framework, namely PerSRV, structured into offline calculations and online processing modules.The online retrieval part follows the paradigm of relevant recall and personalized ranking, supported by the offline precalculation parts, which are sticker semantic understanding, utility evaluation and personalization modules.Firstly, for sticker-level semantic understanding, we supervised fine-tuned LLaVA-1.5-7B to generate human-like sticker semantics, complemented by textual content extracted from figures and historical interaction queries.Secondly, we investigate three crowd-sourcing metrics for sticker utility evaluation.Thirdly, we cluster style centroids based on users' historical interactions to achieve personal preference modeling.Finally, we evaluate our proposed PerSRV method on a public sticker retrieval dataset from WeChat 1 , containing 543,098 candidates and 12,568 interactions.Experimental results show that PerSRV significantly outperforms existing methods in multi-modal sticker retrieval.Additionally, our supervised fine-tuned VLM delivers notable improvements in sticker semantic understandings.The code 2 * Both authors contributed equally to this research.

With the rapid development of Large Language Models (LLMs), recent studies employed LLMs as recommenders to provide personalized information services for distinct users. Despite efforts to improve the accuracy of LLM-based recommendation models, relatively little attention is paid to beyond-utility dimensions. Moreover, there are unique evaluation aspects of LLM-based recommendation models, which have been largely ignored. To bridge this gap, we explore four new evaluation dimensions and propose a multidimensional evaluation framework. The new evaluation dimensions include: 1) history length sensitivity, 2) candidate position bias, 3) generation-involved performance, and 4) hallucinations. All four dimensions have the potential to impact performance, but are largely unnecessary for consideration in traditional systems. Using this multidimensional evaluation framework, along with traditional aspects, we evaluate the performance of seven LLM-based recommenders, with three prompting strategies, comparing them with six traditional models on both ranking and re-ranking tasks on four datasets. We find that LLMs excel at handling tasks with prior knowledge and shorter input histories in the ranking setting, and perform better in the re-ranking setting, beating traditional models across multiple dimensions. However, LLMs exhibit substantial candidate position bias issues, and some models hallucinate nonexistent items much more often than others. We intend our evaluation framework and observations to benefit future research on the use of LLMs as recommenders. The code and data are available at https://github.com/JiangDeccc/EvaLLMasRecommender.

Providing reasonable explanations for a specific suggestion given by the recommender can help users trust the system more. As logic rule-based inference is concise, transparent, and aligned with human cognition, it can be adopted to improve the interpretability of recommendation models. Previous work that interprets user preference with logic rules merely focuses on the construction of rules while neglecting the usage of feature embeddings. This limits the model in capturing implicit relationships between features. In this article, we aim to improve both the effectiveness and explainability of recommendation models by simultaneously representing logic rules and feature embeddings. We propose a novel model-intrinsic explainable recommendation method named Feature-Enhanced Neural Collaborative Reasoning (FENCR) . The model automatically extracts representative logic rules from massive possibilities in a data-driven way. In addition, we utilize feature interaction-based neural modules to represent logic operators on embeddings. Experiments on two large public datasets show our model outperforms state-of-the-art neural logical recommendation models. Further case analyses demonstrate that FENCR can derive reasonable rules, indicating its high robustness and expandability. 1

With an increasing number of music tracks available online, music recommender systems have become popular and ubiquitous. Previous research indicates that people’s preferences, especially in music, dynamically change with various factors, such as surrounding situations and emotional status. However, few existing public recommendation datasets contain such situation or emotion information. Therefore, we constructed SiTunes, a situational music recommendation dataset with rich physiological and psychological signals. We collected the data through a three-stage user study, including: (1) recorded users’ inherent music preference in a lab setting (Stage 1), (2) recorded physiological and environmental situations by smart wristband devices in users’ daily life, and provided psychological and rating feedback for music recommended by traditional recommenders (Stage 2) and (3) by situation-aware recommenders (Stage 3). The experiments were conducted with strict privacy concerns and ethical approval. The dataset contains over 2000 listening logs from 30 users on over 300 music tracks. SiTunes serves as a valuable resource for future studies on situational recommenders and user understanding in recommendation. The dataset is available at https://github.com/JiayuLi-997/SiTunes_dataset/.

Providing natural language-based explanations to justify recommendations helps to improve users' satisfaction and gain users' trust. However, as current explanation generation methods are commonly trained with an objective to mimic existing user reviews, the generated explanations are often not aligned with the predicted ratings or some important features of the recommended items, and thus, are suboptimal in helping users make informed decision on the recommendation platform. To tackle this problem, we propose a flexible model-agnostic method named MMI (Maximizing Mutual Information) framework to enhance the alignment between the generated natural language explanations and the predicted rating/important item features. Specifically, we propose to use mutual information (MI) as a measure for the alignment and train a neural MI estimator. Then, we treat a well-trained explanation generation model as the backbone model and further fine-tune it through reinforcement learning with guidance from the MI estimator, which rewards a generated explanation that is more aligned with the predicted rating or a pre-defined feature of the recommended item. Experiments on three datasets demonstrate that our MMI framework can boost different backbone models, enabling them to outperform existing baselines in terms of alignment with predicted ratings and item features. Additionally, user studies verify that MI-enhanced explanations indeed facilitate users' decisions and are favorable compared with other baselines due to their better alignment properties.

Graph-based models and contrastive learning have emerged as prominent methods in Collaborative Filtering (CF). While many existing models in CF incorporate these methods in their design, there seems to be a limited depth of analysis regarding the foundational principles behind them. This paper bridges graph convolution, a pivotal element of graph-based models, with contrastive learning through a theoretical framework. By examining the learning dynamics and equilibrium of the contrastive loss, we offer a fresh lens to understand contrastive learning via graph theory, emphasizing its capability to capture high-order connectivity. Building on this analysis, we further show that the graph convolutional layers often used in graph-based models are not essential for high-order connectivity modeling and might contribute to the risk of oversmoothing. Stemming from our findings, we introduce Simple Contrastive Collaborative Filtering (SCCF), a simple and effective algorithm based on a naive embedding model and a modified contrastive loss. The efficacy of the algorithm is demonstrated through extensive experiments across four public datasets. The experiment code is available at https://github.com/wu1hong/SCCF.

With the applications of recommendation systems rapidly expanding, an increasing number of studies have focused on every aspect of recommender systems with different data inputs, models, and task settings. Therefore, a flexible library is needed to help researchers implement the experimental strategies they require. Existing open libraries for recommendation scenarios have enabled reproducing various recommendation methods and provided standard implementations. However, these libraries often impose certain restrictions on data and seldom support the same model to perform different tasks and input formats, limiting users from customized explorations. To fill the gap, we propose ReChorus2.0, a modular and task-flexible library for recommendation researchers. Based on ReChorus, we upgrade the supported input formats, models, and training&evaluation strategies to help realize more recommendation tasks with more data types. The main contributions of ReChorus2.0 include: (1) Realization of complex and practical tasks, including re-ranking and CTR prediction tasks; (2) Inclusion of various context-aware and re-ranking recommenders; (3) Extension of existing and new models to support different tasks with the same models; (4) Support of highly-customized input with impression logs, negative items, or click labels, as well as user, item, and situation contexts. To summarize, ReChorus2.0 serves as a comprehensive and flexible library that better addresses the practical problems in the recommendation scenario and caters to more diverse research needs. The implementation and detailed tutorials of ReChorus2.0 can be found at https://github.com/THUwangcy/ReChorus.

From e-commerce to music and news, recommender systems are tailored to specific scenarios. While researching generic models applicable to various scenarios is crucial, studying recommendations based on the unique characteristics of a specific and vital scenario holds both research and, more importantly, practical value.

The explainability of recommender systems has attracted significant attention in academia and industry. Many efforts have been made for explainable recommendations, yet evaluating the quality of the explanations remains a challenging and unresolved issue. In recent years, leveraging LLMs as evaluators presents a promising avenue in Natural Language Processing tasks (e.g., sentiment classification, information extraction), as they perform strong capabilities in instruction following and common-sense reasoning. However, evaluating recommendation explanatory texts is different from these NLG tasks, as its criteria are related to human perceptions and are usually subjective.

As recommender systems become pervasive in various scenarios, cross-domain recommenders (CDR) are proposed to enhance the performance of one target domain with data from other related source domains. However, irrelevant information from the source domain may instead degrade target domain performance, which is known as the negative transfer problem. Most existing efforts to tackle this issue primarily focus on designing adaptive representations for overlapped users. Whereas, these methods rely on the learned representations of the model, lacking explicit constraints to filter irrelevant source-domain collaborative information for the target domain, which limits their cross-domain transfer capability.

LLM-based agents have gained considerable attention for their decision-making skills and ability to handle complex tasks.Recognizing the current gap in leveraging agent capabilities for multiagent collaboration in recommendation systems, we introduce MACRec, a novel framework designed to enhance recommendation systems through multi-agent collaboration.Unlike existing work on using agents for user/item simulation, we aim to deploy multiagents to tackle recommendation tasks directly.In our framework, recommendation tasks are addressed through the collaborative efforts of various specialized agents, including Manager, User/Item Analyst, Reflector, Searcher, and Task Interpreter, with different working flows.Furthermore, we provide application examples of how developers can easily use MACRec on various recommendation tasks, including rating prediction, sequential recommendation, conversational recommendation, and explanation generation of recommendation results.The framework and demonstration video are publicly available at https://github.com/wzf2000/MACRec.

Sequential recommender systems predict items that may interest users by modeling their preferences based on historical interactions. Traditional sequential recommendation methods rely on capturing implicit collaborative filtering signals among items. Recent relation-aware sequential recommendation models have achieved promising performance by explicitly incorporating item relations into the modeling of user historical sequences, where most relations are extracted from knowledge graphs. However, existing methods rely on manually predefined relations and suffer the sparsity issue, limiting the generalization ability in diverse scenarios with varied item relations.

Reinforcement Learning (RL)-Based Recommender Systems (RSs) have gained rising attention for their potential to enhance long-term user engagement. However, research in this field faces challenges, including the lack of user-friendly frameworks, inconsistent evaluation metrics, and difficulties in reproducing existing studies. To tackle these issues, we introduce EasyRL4Rec, an easy-to-use code library designed specifically for RL-based RSs. This library provides lightweight and diverse RL environments based on five public datasets and includes core modules with rich options, simplifying model development. It provides unified evaluation standards focusing on long-term outcomes and offers tailored designs for state modeling and action representation for recommendation scenarios. Furthermore, we share our findings from insightful experiments with current methods. EasyRL4Rec seeks to facilitate the model development and experimental process in the domain of RL-based RSs. The library is available for public use.

Fairness of recommender systems (RS) has attracted increasing attention recently. Based on the involved stakeholders, the fairness of RS can be divided into user fairness, item fairness, and two-sided fairness which considers both user and item fairness simultaneously. However, we argue that the intersectional two-sided unfairness may still exist even if the RS is two-sided fair, which is observed and shown by empirical studies on real-world data in this paper, and has not been well-studied previously. To mitigate this problem, we propose a novel approach called Intersectional Two-sided Fairness Recommendation (ITFR). Our method utilizes a sharpness-aware loss to perceive disadvantaged groups, and then uses collaborative loss balance to develop consistent distinguishing abilities for different intersectional groups. Additionally, predicted score normalization is leveraged to align positive predicted scores to fairly treat positives in different intersectional groups. Extensive experiments and analyses on three public datasets show that our proposed approach effectively alleviates the intersectional two-sided unfairness and consistently outperforms previous state-of-the-art methods.

Item representation learning (IRL) plays an essential role in recommender systems, especially for sequential recommendation. Traditional sequential recommendation models usually utilize ID embeddings to represent items, which are not shared across different domains and lack the transferable ability. Recent studies use pre-trained language models (PLM) for item text embeddings (text-based IRL) that are universally applicable across domains. However, the existing text-based IRL is unaware of the important collaborative filtering (CF) information. In this paper, we propose CoWPiRec, an approach of Collaborative Word-based Pre-trained item representation for Recommendation. To effectively incorporate CF information into text-based IRL, we convert the item-level interaction data to a word graph containing word-level collaborations. Subsequently, we design a novel pre-training task to align the word-level semantic-and CF-related item representation. Extensive experimental results on multiple public datasets demonstrate that compared to state-of-the-art transferable sequential recommenders, CoWPiRec achieves significantly better performances in both fine-tuning and zero-shot settings for cross-scenario recommendation and effectively alleviates the cold-start issue. The code is available at: https://github.com/ysh-1998/CoWPiRec.

Calibration in recommender systems ensures that the user’s interests distribution over groups of items is reflected with their corresponding proportions in the recommendation, which has gained increasing attention recently. For example, a user who watched 80 entertainment videos and 20 knowledge videos is expected to receive recommendations comprising about 80% entertainment and 20% knowledge videos as well. However, with the increasing calls for responsible recommendation, it has become inadequate to just match users’ historical behaviors especially when items are grouped by their qualities, which could result in undesired effects at the system level (e.g., overwhelming clickbaits). In this paper, we envision the two-sided calibration task that not only matches the users’ past interests distribution (user-level calibration) but also guarantees an overall target exposure distribution of different item groups (system-level calibration). The target group exposure distribution can be explicitly pursued by users, platform owners, and even the law (e.g., the platform owners expect about 50% knowledge video recommendation on the whole). To support this scenario, we propose a post-processing method named PCT. PCT first solves personalized calibration targets that minimize the changes in users’ historical interest distributions while ensuring the overall target group exposure distribution. Then, PCT reranks the original recommendation lists according to personalized calibration targets to generate both relevant and two-sided calibrated recommendations. Extensive experiments demonstrate the superior performance of the proposed method compared to calibrated and fairness-aware recommendation approaches.

Ranking ensemble is a critical component in real recommender systems. When a user visits a platform, the system will prepare several item lists, each of which is generally from a single behavior objective recommendation model. As multiple behavior intents, e.g., both clicking and buying some specific item category, are commonly concurrent in a user visit, it is necessary to integrate multiple single-objective ranking lists into one. However, previous work on rank aggregation mainly focused on fusing homogeneous item lists with the same objective while ignoring ensemble of heterogeneous lists ranked with different objectives with various user intents.

In the era of information explosion, numerous items emerge every day, especially in feed scenarios. Due to the limited system display slots and user browsing attention, various recommendation systems are designed not only to satisfy users' personalized information needs but also to allocate items' exposure. However, recent recommendation studies mainly focus on modeling user preferences to present satisfying results and maximize user interactions, while paying little attention to developing item-side fair exposure mechanisms for rational information delivery. This may lead to serious resource allocation problems on the item side, such as the Snowball Effect. Furthermore, unfair exposure mechanisms may hurt recommendation performance. In this paper, we call for a shift of attention from modeling user preferences to developing fair exposure mechanisms for items. We first conduct empirical analyses of feed scenarios to explore exposure problems between items with distinct uploaded times. This points out that unfair exposure caused by the time factor may be the major cause of the Snowball Effect. Then, we propose to explicitly model item-level customized timeliness distribution, Global Residual Value (GRV), for fair resource allocation. This GRV module is introduced into recommendations with the designed Timeliness-aware Fair Recommendation Framework (TaFR). Extensive experiments on two datasets demonstrate that TaFR achieves consistent improvements with various backbone recommendation models. By modeling item-side customized Global Residual Value, we achieve a fairer distribution of resources and, at the same time, improve recommendation performance.

Overfitting is a common problem in machine learning, which means the model too closely fits the training data while performing poorly in the test data. Among various methods of coping with overfitting, dropout is one of the representative ways. From randomly dropping neurons to dropping neural structures, dropout has achieved great success in improving model performances. Although various dropout methods have been designed and widely applied in past years, their effectiveness, application scenarios, and contributions have not been comprehensively summarized and empirically compared by far. It is the right time to make a comprehensive survey. In this paper, we systematically review previous dropout methods and classify them into three major categories according to the stage where dropout operation is performed. Specifically, more than seventy dropout methods published in top AI conferences or journals (e.g., TKDE, KDD, TheWebConf, SIGIR) are involved. The designed taxonomy is easy to understand and capable of including new dropout methods. Then, we further discuss their application scenarios, connections, and contributions. To verify the effectiveness of distinct dropout methods, extensive experiments are conducted on recommendation scenarios with abundant heterogeneous information. Finally, we propose some open problems and potential research directions about dropout that worth to be further explored.

Recommendation systems play an important role in alleviating the information overload issue. Generally, a recommendation model is trained to discern between positive (liked) and negative (disliked) instances for each user. However, under the open-world assumption, there are only positive instances but no negative instances from users’ implicit feedback, which poses the imbalanced learning challenge of lacking negative samples. To address this, two types of learning strategies have been proposed before, the negative sampling strategy and non-sampling strategy. The first strategy samples negative instances from missing data (i.e., unlabeled data), while the non-sampling strategy regards all the missing data as negative. Although learning strategies are known to be essential for algorithm performance, the in-depth comparison of negative sampling and non-sampling has not been sufficiently explored by far. To bridge this gap, we systematically analyze the role of negative sampling and non-sampling for implicit recommendation in this work. Specifically, we first theoretically revisit the objection of negative sampling and non-sampling. Then, with a careful setup of various representative recommendation methods, we explore the performance of negative sampling and non-sampling in different scenarios. Our results empirically show that although negative sampling has been widely applied to recent recommendation models, it is non-trivial for uniform sampling methods to show comparable performance to non-sampling learning methods. Finally, we discuss the scalability and complexity of negative sampling and non-sampling and present some open problems and future research topics that are worth being further explored.

As recommender systems become increasingly important in daily human decision-making, users are demanding convincing explanations to understand why they get the specific recommendation results. Although a number of explainable recommender systems have recently been proposed, there still lacks an understanding of what users really need in a recommendation explanation. The actual reason behind users’ intention to examine and consume (e.g., click and watch a movie) can be the window to answer this question and is named as self-explanation in this work. In addition, humans usually make recommendations accompanied by explanations, but there remain fewer studies on how humans explain and what we can learn from human-generated explanations. To investigate these questions, we conduct a novel multi-role, multi-session user study in which users interact with multiple types of system-generated explanations as well as human-generated explanations, namely peer-explanation . During the study, users’ intentions, expectations, and experiences are tracked in several phases, including before and after the users are presented with an explanation and after the content is examined. Through comprehensive investigations, three main findings have been made: First, we observe not only the positive but also the negative effects of explanations, and the impact varies across different types of explanations. Moreover, human-generated explanation, peer-explanation , performs better in increasing user intentions and helping users to better construct preferences, which results in better user satisfaction. Second, based on users’ self-explanation , the information accuracy is measured and found to be a major factor associated with user satisfaction. Some other factors, such as unfamiliarity and similarity, are also discovered and summarized. Third, through annotations of the information aspects used in the human-generated self-explanation and peer-explanation , patterns of how humans explain are investigated, including what information and how much information is utilized. In addition, based on the findings, a human-inspired explanation approach is proposed and found to increase user satisfaction, revealing the potential improvement of further incorporating more human patterns in recommendation explanations. These findings have shed light on the deeper understanding of the recommendation explanation and further research on its evaluation and generation. Furthermore, the collected data, including human-generated explanations by both the external peers and the users’ selves, will be released to support future research works on explanation evaluation.

Recommender systems are an essential tool to relieve the information overload challenge and play an important role in people’s daily lives. Since recommendations involve allocations of social resources (e.g., job recommendation), an important issue is whether recommendations are fair. Unfair recommendations are not only unethical but also harm the long-term interests of the recommender system itself. As a result, fairness issues in recommender systems have recently attracted increasing attention. However, due to multiple complex resource allocation processes and various fairness definitions, the research on fairness in recommendation is scattered. To fill this gap, we review over 60 papers published in top conferences/journals, including TOIS, SIGIR, and WWW. First, we summarize fairness definitions in the recommendation and provide several views to classify fairness issues. Then, we review recommendation datasets and measurements in fairness studies and provide an elaborate taxonomy of fairness methods in the recommendation. Finally, we conclude this survey by outlining some promising future directions.

Sequential recommendation has become a trending research topic for its capability to capture dynamic user intents based on historical interaction sequence. To train a sequential recommendation model, it is a common practice to optimize the next-item recommendation task with a pairwise ranking loss. In this paper, we revisit this typical training method from the perspective of contrastive learning and find it can be taken as a specialized contrastive learning task conceptually and mathematically, named context-target contrast . Further, to leverage other self-supervised signals in user interaction sequences, we propose another contrastive learning task to encourage sequences after augmentation, as well as sequences with the same target item, to have similar representations, called context-context contrast . A general framework, ContraRec, is designed to unify the two kinds of contrast signals, leading to a holistic joint-learning framework for sequential recommendation with different contrastive learning tasks. Besides, various sequential recommendation methods (e.g., GRU4Rec, Caser, and BERT4Rec) can be easily integrated as the base sequence encoder in our ContraRec framework. Extensive experiments on three public datasets demonstrate that ContraRec achieves superior performance compared to state-of-the-art sequential recommendation methods.

Result ranking is one of the major concerns for Web search technologies. Most existing methodologies rank search results in descending order of relevance. To model the interactions among search results, reinforcement learning (RL algorithms have been widely adopted for ranking tasks. However, the online training of RL methods is time and resource consuming at scale. As an alternative, learning ranking policies in the simulation environment is much more feasible and efficient. In this article, we propose two different simulation environments for the offline training of the RL ranking agent: the Context-aware Click Simulator (CCS) and the Fine-grained User Behavior Simulator with GAN (UserGAN). Based on the simulation environment, we also design a User Behavior Simulation for Reinforcement Learning (UBS4RL) re-ranking framework, which consists of three modules: a feature extractor for heterogeneous search results, a user simulator for collecting simulated user feedback, and a ranking agent for generation of optimized result lists. Extensive experiments on both simulated and practical Web search datasets show that (1) the proposed user simulators can capture and simulate fine-grained user behavior patterns by training on large-scale search logs, (2) the temporal information of user searching process is a strong signal for ranking evaluation, and (3) learning ranking policies from the simulation environment can effectively improve the search ranking performance.

Molecular property prediction is essential for drug discovery. In recent years, deep learning methods have been introduced to this area and achieved state-of-the-art performances. However, most of existing methods ignore the intrinsic relations between molecular properties which can be utilized to improve the performances of corresponding prediction tasks. In this paper, we propose a new approach, namely Physics properties Enhanced Molecular Property prediction (PEMP), to utilize relations between molecular properties revealed by previous physics theory and physical chemistry studies. Specifically, we enhance the training of the chemical and physiological property predictors with related physics property prediction tasks. We design two different methods for PEMP, respectively based on multi-task learning and transfer learning. Both methods include a model-agnostic molecule representation module and a property prediction module. In our implementation, we adopt both the state-of-the-art molecule embedding models under the supervised learning paradigm and the pretraining paradigm as the molecule representation module of PEMP, respectively. Experimental results on public benchmark MoleculeNet show that the proposed methods have the ability to outperform corresponding state-of-the-art models.

Image classification is a classical machine learning task and has been widely used. Due to the high costs of annotation and data collection in real scenarios, few-shot learning has become a vital technique to improve image classification performances. However, most existing few-shot image classification methods only focus on modeling the global image feature or image local patches, which ignore the global-local interactions. In this study, we propose a new method, named GL-ViT, to integrate both global and local features to fully exploit the few-shot samples for image classification. Firstly, we design a feature extractor module to calculate the interactions between the global representation and local patch embeddings, where ViT is also adopted to achieve efficient and effective image representation. Then, Earth Mover's Distance is adopted to measure the similarity between two images. Abundant Experimental results on several widely-used open datasets show that GL-ViT outperforms state-of-the-art algorithms significantly, and our ablation studies also verify the effectiveness of both global-local features.

Sequential recommendation aims at predicting the next item that the user may be interested in given the historical interaction sequence. Typical neural models derive a single history embedding to represent the user's interests. Moving one step forward, recent studies point out that multiple sequence embeddings can help to better capture multi-faceted user interests. However, when ranking candidate items, these methods usually adopt the greedy inference strategy. This approach uses the best matching interest for each candidate item to calculate the ranking score, neglecting the target interest distribution in different contexts, which might lead to incompatibility with the current user intent. In this paper, we propose to enhance multi-interest recommendation by predicting the target user interest with a separate interest predictor and a specifically designed distillation loss. The proposed framework consists of two modules: the 1) multi-interest extractor to generate multiple embeddings regarding different user interests; and the 2) target-interest predictor to predict the interest distribution in the current context, which will be further utilized to dynamically aggregate multi-interest embeddings. To provide explicit supervision signals to the target-interest predictor, we devise a target-interest distillation loss that uses the similarity between the target item and multi-interest embeddings as the soft label of the target interest. This helps the target-interest predictor to accurately predict the user interest at the inference stage and enhances its generalization ability. Extensive experiments on three real-world datasets show the effectiveness and flexibility of the proposed framework.

The item fairness issue has become one of the significant concerns with the development of recommender systems in recent years, focusing on whether items' exposures are consistent with their utilities. So the measurement of item unfairness depends on the modeling of item utility, and most previous approaches estimated item utility simply based on user-item interaction logs in recommender systems. The Click-through rate (CTR) is the most popular one. However, we argue that these types of item utilities (named observed utility here) measurements may result in unfair exposures of items. The number of exposure for each item is uneven, and recommendation methods select the exposure audiences (users).

Collaborative filtering (CF) plays a critical role in the development of recommender systems. Most CF methods utilize an encoder to embed users and items into the same representation space, and the Bayesian personalized ranking (BPR) loss is usually adopted as the objective function to learn informative encoders. Existing studies mainly focus on designing more powerful encoders (e.g., graph neural network) to learn better representations. However, few efforts have been devoted to investigating the desired properties of representations in CF, which is important to understand the rationale of existing CF methods and design new learning objectives. In this paper, we measure the representation quality in CF from the perspective of alignment and uniformity on the hypersphere. We first theoretically reveal the connection between the BPR loss and these two properties. Then, we empirically analyze the learning dynamics of typical CF methods in terms of quantified alignment and uniformity, which shows that better alignment or uniformity both contribute to higher recommendation performance. Based on the analyses results, a learning objective that directly optimizes these two properties is proposed, named DirectAU. We conduct extensive experiments on three public datasets, and the proposed learning framework with a simple matrix factorization model leads to significant performance improvements compared to state-of-the-art CF methods.

This paper presents a neural information retrieval pipeline that integrates cooperative learning of query reformulation and neural retrieval models. Our pipeline first exploits an automatic query reformulator to reformulate the user-issued query and then submits the reformulated query to the neural retrieval model. We simultaneously optimize the quality of reformulated queries and ranking performance with an alternate training strategy where query reformulator and neural retrieval model learn from the feedback of each other. Besides, we incorporate knowledge information into automatic query reformulation. The reformulated queries are further improved and contribute to a better ranking performance of the following neural retrieval model. We study two representative neural retrieval models KNRM and BERT in our pipeline. Experiments on two datasets show that our pipeline consistently improves the retrieval performance of the original neural retrieval models while only increases negligible time on automatic query reformulation.

Recommendation in legal scenario (Legal-Rec) is a specialized recommendation task that aims to provide potential helpful legal documents for users. While there are mainly three differences compared with traditional recommendation: (1) Both the structural connections and textual contents of legal information are important in the Legal-Rec scenario, which means feature fusion is very important here. (2) Legal-Rec users prefer the newest legal cases (the latest legal interpretation and legal practice), which leads to a severe new-item problem. (3) Different from users in other scenarios, most Legal-Rec users are expert and domain-related users. They often concentrate on several topics and have more stable information needs. So it is important to accurately model user interests here. To the best of our knowledge, existing recommendation work cannot handle these challenges simultaneously. To address these challenges, we propose a legal information enhanced graph neural network–based recommendation framework (LegalGNN). First, a unified legal content and structure representation model is designed for feature fusion, where the Heterogeneous Legal Information Network (HLIN) is constructed to connect the structural features (e.g., knowledge graph) and contextual features (e.g., the content of legal documents) for training. Second, to model user interests, we incorporate the queries users issued in legal systems into the HLIN and link them with both retrieved documents and inquired users. This extra information is not only helpful for estimating user preferences, but also valuable for cold users/items (with less interaction history) in this scenario. Third, a graph neural network with relational attention mechanism is applied to make use of high-order connections in HLIN for Legal-Rec. Experimental results on a real-world legal dataset verify that LegalGNN outperforms several state-of-the-art methods significantly. As far as we know, LegalGNN is the first graph neural model for legal recommendation.

While batch evaluation plays a central part in Information Retrieval (IR) research, most evaluation metrics are based on user models which mainly focus on browsing and clicking behaviors. As users' perceived satisfaction may also be impacted by their search intent, constructing different user models across various search intent may help design better evaluation metrics. However, user intents are usually unobservable in practice. As query reformulating behaviors may reflect their search intents to a certain extent and highly correlate with users' perceived satisfaction for a specific query, these observable factors may be beneficial for the design of evaluation metrics. How to incorporate the search intent behind query reformulation into user behavior and satisfaction models remains under-investigated. To investigate the relationships among query reformulations, search intent, and user satisfaction, we explore a publicly available web search dataset and find that query reformulations can be a good proxy for inferring user intent, and therefore, reformulating actions may be beneficial for designing better web search effectiveness metrics. A group of Reformulation-Aware Metrics (RAMs) is then proposed to improve existing click model-based metrics. Experimental results on two public session datasets have shown that RAMs have significantly higher correlations with user satisfaction than existing evaluation metrics. In the robustness test, we have found that RAMs can achieve good performance when only a small proportion of satisfaction training labels are available. We further show that RAMs can be directly applied in a new dataset for offline evaluation once trained. This work shows the possibility of designing better evaluation metrics by incorporating fine-grained search context factors.

News recommendation plays an indispensable role in acquiring daily news for users. Previous studies make great efforts to model high-order feature interactions between users and items, where various neural models are applied (e.g., RNN, GNN). However, we find that seldom efforts are made to get better representations for news. Most previous methods simply adopt pre-trained word embeddings to represent news and also suffer from cold-start users.

User's leaving from the system without further return, called user churn, is a severe negative signal in online games. Therefore, churn prediction and intervention are of great value for improving players' experiences and system performance. However, the problem has not been well-studied in the game scenario. Especially, some crucial factors, such as game difficulty, have not been considered for large-scale churn analysis. In this paper, a novel Difficulty-Aware Framework (DAF) for churn prediction and intervention is proposed. Firstly, a Difficulty Flow for each user is proposed, which is utilized to derive users' Personalized Perceived Difficulty during the game process. Then, a survival analysis modelD-Cox-Time is designed to model the Dynamic Influence of Perceived Difficulty on player churn intention. Finally, thePersonalized Perceived Difficulty ~(PPD) andDynamic Difficulty Influence ~(DDI) are incorporated to churn prediction and intervention. The proposed DAF framework has been specified in a real-world puzzle game as an example for churn prediction and intervention. Extensive offline experiments show significant improvements in churn prediction by introducing difficulty-related features. Besides, we conduct an online intervention system to adjust difficulty dynamically in the online game. A/B test results verify that the proposed intervention system enhances user retention and engagement significantly. To the best of our knowledge, it is the first framework in games that illustrates an in-depth understanding and leveraging dynamic and personalized perceived difficulty during game playing, which is easy to be integrated with various churn prediction and intervention models.

User behaviors and experiences are the fundamental parts of information retrieval systems, but are often difficult to collect, bringing challenges to both applications and research. Recently, researchers have been exploring more fine-grained user behavior than simple clicks, such as time patterns, mouse/scroll patterns, etc., with their own specific laboratory experimental platforms. However, the lack of public available toolkits for logging user behaviors and experiences leads to difficulties on field study of remote user experiments in real scenarios. In this work, we propose a Privacy-Aware Remote User Logging Tool for remotely collecting user behaviors and explicit experience feedback, with a special care for user privacy. With this tool, participants can conduct the user experiments remotely without time and location constraints, giving researchers the possibility to observe users' more natural behaviors and experiences.

Knowledge graphs are widely used in information retrieval as they can enhance our semantic understanding of queries and documents. The main idea is to consider entities and entity relationships as side information. Although existing work has achieved improvements in retrieval effectiveness by incorporating information from knowledge graphs into retrieval models, few studies have leveraged knowledge graphs in understanding users' search behavior. We investigate user behavior during session search from the perspective of a knowledge graph. We conduct a query log-based analysis of users' query reformulation and document clicking behavior. Based on a large-scale commercial query log and a knowledge graph, we find new user behavior patterns in terms of query reformulation and document clicking. Our study deepens our understanding of user behavior in session search and provides implications to help improve retrieval models with knowledge graphs.

The evaluation of recommender systems relies on user preference data, which is difficult to acquire directly because of its subjective nature. Current recommender systems widely utilize users' historical interactions as implicit or explicit feedback, but such data usually suffers from various types of bias. Little work has been done on collecting and understanding user's personal preferences via third-party annotations. External assessments, that is, annotations made by assessors who are not the systems' users, have been widely used in information search scenarios. Is it possible to use external assessments to construct user preference labels? This paper presents the first attempt to incorporate external assessments into preference labeling and recommendation evaluation. The aim is to verify the possibility and reliability of external assessments for personalized recommender systems. We collect both users' real preferences and assessors' estimated preferences through a multi-role, multi-session user study. By investigating the inter-assessor agreement and user-assessor consistency, we demonstrate the reasonable stability and high accuracy of external preference assessments. Furthermore, we investigate the usage of external assessments in system evaluation. A higher degree of consistency with users' online feedback is observed, even better than traditional history-based online evaluation. Our findings show that external assessments can be used for assessing user preference labels and evaluating systems in personalized recommendation scenarios.

Knowledge tracing (KT) aims to model students' knowledge level based on their historical performance, which plays an important role in computer-assisted education and adaptive learning. Recent studies try to take temporal effects of past interactions into consideration, such as the forgetting behavior. However, existing work mainly relies on time-related features or a global decay function to model the time-sensitive effects. Fine-grained temporal dynamics of different cross-skill impacts have not been well studied (named as temporal cross-effects). For example, cross-effects on some difficult skills may drop quickly, and the effects caused by distinct previous interactions may also have different temporal evolutions, which cannot be captured in a global way. In this work, we investigate fine-grained temporal cross-effects between different skills in KT. We first validate the existence of temporal cross-effects in real-world datasets through empirical studies. Then, a novel model, HawkesKT, is proposed to explicitly model the temporal cross-effects inspired by the point process, where each previous interaction will have different time-sensitive impacts on the mastery of the target skill. HawkesKT adopts two components to model temporal cross-effects: 1) mutual excitation represents the degree of cross-effects and 2) kernel function controls the adaptive temporal evolution. To the best of our knowledge, we are the first to introduce Hawkes process to model temporal cross-effects in KT. Extensive experiments on three benchmark datasets show that HawkesKT is superior to state-of-the-art KT methods. Remarkably, our method also exhibits excellent interpretability and shows significant advantages in training efficiency, which makes it more applicable in real-world large-scale educational settings.

Relevance measures the relation between query and document which contains several different dimensions, e.g., semantic similarity, topical relatedness, cognitive relevance (the relations in the aspect of knowledge), usefulness, timeliness, utility and so on. However, existing retrieval models mainly focus on semantic similarity and cognitive relevance while ignore other possible dimensions to model relevance. Topical relatedness, as an important dimension to measure relevance, is not well studied in existing neural information retrieval. In this paper, we propose a Topic Enhanced Knowledge-aware retrieval Model (TEKM) that jointly learns semantic similarity, knowledge relevance and topical relatedness to estimate relevance between query and document. We first construct a neural topic model to learn topical information and generate topic embeddings of a query. Then we combine the topic embeddings with a knowledge-aware retrieval model to estimate different dimensions of relevance. Specifically, we exploit kernel pooling to soft match topic embeddings with word and entity in a unified embedding space to generate fine-grained topical relatedness. The whole model is trained in an end-to-end manner. Experiments on a large-scale publicly available benchmark dataset show that TEKM outperforms existing retrieval models. Further analysis also shows how topic relatedness is modeled to improve traditional retrieval model with semantic similarity and knowledge relevance.

Understanding user intent is essential for various retrieval tasks. By leveraging contextual information within sessions, e.g., query history and user click behaviors, search systems can capture user intent more accurately and thus perform better. However, most existing systems only consider intra-session contexts and may suffer from the problem of lacking contextual information, because short search sessions account for a large proportion in practical scenarios. We believe that in these scenarios, considering more contexts, e.g., cross-session dependencies, may help alleviate the problem and contribute to better performance. Therefore, we propose a novel Hybrid framework for Session Context Modeling (HSCM), which realizes session-level multi-task learning based on the self-attention mechanism. To alleviate the problem of lacking contextual information within current sessions, HSCM exploits the cross-session contexts by sampling user interactions under similar search intents in the historical sessions and further aggregating them into the local contexts. Besides, application of the self-attention mechanism rather than RNN-based frameworks in modeling session-level sequences also helps (1) better capture interactions within sessions, (2) represent the session contexts in parallelization. Experimental results on two practical search datasets show that HSCM not only outperforms strong baseline solutions such as HiNT, CARS, and BERTserini in document ranking, but also performs significantly better than most existing query suggestion methods. According to the results in an additional experiment, we have also found that HSCM is superior to most ranking models in click prediction.

User intention is an important factor to be considered for recommender systems, which always changes dynamically in different contexts. Recent studies (represented by sequential recommendation) begin to focus on predicting what users want beyond what users like, which are better at capturing user intention and have attracted a surge of interest. However, user intention modeling is non-trivial, because it is generally influenced by various factors, among which item relations and their temporal evolutionary effects are of great importance. For example, consumption of a cellphone will have varying impacts on the demands for its relational items: For complements, the demands are likely to be promoted in the short term; while for substitutes, the long-term effect may take advantage, because users do not need another cellphone immediately. Moreover, the temporal evolutions of different relational effects vary across different domains, which makes it challenging to adaptively take them into consideration. As a result, most existing studies only loosely incorporate item relations by encoding their semantics into embeddings, neglecting fine-grained time-aware effects. In this work, we propose Knowledge-aware Dynamic Attention (KDA) to take both relational effects and their temporal evolutions into consideration. Specifically, to model dynamic impacts of historical relational interactions on user intention, we aggregate the history sequence into relation-specific embeddings, where the attention weight consists of two parts. First, we measure the relational intensity between historical items and the target item to model the absolute degree of influence in terms of each relation. Second, to model how the relational effects drift with time, we innovatively introduce Fourier transform with learnable frequency-domain embeddings to estimate temporal decay functions of different relations adaptively. Subsequently, the self-attention mechanism is leveraged to derive the final representation of the whole history sequence, which reflects the dynamic user intention and will be applied to generate the recommendation list. Extensive experiments in three real-world datasets indicate the proposed KDA model significantly outperforms the state-of-the-art methods on the Top- K recommendation task. Moreover, the proposed Fourier-based method opens up a new avenue to adaptively integrate temporal dynamics into general neural models.

Neural ranking models have recently gained much attention in Information Retrieval community and obtain good ranking performance. However, most of these retrieval models focus on capturing the textual matching signals between query and document but do not consider user behavior information that may be helpful for the retrieval task. Specifically, users' click and query reformulation behavior can be represented by a click-through bipartite graph and a session-flow graph, respectively. Such graph representations contain rich user behavior information and may help us better understand users' search intent beyond the textual information. In this study, we aim to incorporate this rich information encoded in these two graphs into existing neural ranking models.

Recent years have witnessed the success of deep neural networks in many research areas. The fundamental idea behind the design of most neural networks is to learn similarity patterns from data for prediction and inference, which lacks the ability of cognitive reasoning. However, the concrete ability of reasoning is critical to many theoretical and practical problems. On the other hand, traditional symbolic reasoning methods do well in making logical inference, but they are mostly hard rule-based reasoning, which limits their generalization ability to different tasks since difference tasks may require different rules. Both reasoning and generalization ability are important for prediction tasks such as recommender systems, where reasoning provides strong connection between user history and target items for accurate prediction, and generalization helps the model to draw a robust user portrait over noisy inputs.

Knowledge graph (KG) contains well-structured external information and has shown to be effective for high-quality recommendation. However, existing KG enhanced recommendation methods have largely focused on exploring advanced neural network architectures to better investigate the structural information of KG. While for model learning, these methods mainly rely on Negative Sampling (NS) to optimize the models for both KG embedding task and recommendation task. Since NS is not robust (e.g., sampling a small fraction of negative instances may lose lots of useful information), it is reasonable to argue that these methods are insufficient to capture collaborative information among users, items, and entities.

Modeling large scale and rare-interaction users are the two major challenges in recommender systems, which derives big gaps between researches and applications. Facing to millions or even billions of users, it is hard to store and leverage personalized preferences with a user embedding matrix in real scenarios. And many researches pay attention to users with rich histories, while users with only one or several interactions are the biggest part in real systems. Previous studies make efforts to handle one of the above issues but rarely tackle efficiency and cold-start problems together.

Traditional recommender systems mainly aim to model inherent and long-term user preference, while dynamic user demands are also of great importance. Typically, a historical consumption will have impacts on the user demands for its relational items. For instance, users tend to buy complementary items together (iPhone and Airpods) but not substitutive items (Powerbeats and Airpods), although substitutes of the bought one still cater to his/her preference. To better model the effects of history sequence, previous studies introduce the semantics of item relations to capture user demands for recommendation. However, we argue that the temporal evolution of the effects caused by different relations cannot be neglected. In the example above, user demands for headphones can be promoted after a long period when a new one is needed.

Recently session search evaluation has been paid more attention as a realistic search scenario usually involves multiple queries and interactions between users and systems. Evolved from model-based evaluation metrics for a single query, existing session-based metrics also follow a generic framework based on the cascade hypothesis. The cascade hypothesis assumes that lower-ranked search results and later-issued queries receive less attention from users and should therefore be assigned smaller weights when calculating evaluation metrics. This hypothesis gains much success in modeling search users' behavior and designing evaluation metrics, by explaining why users' attention decays on search engine result pages. However, recent studies have found that the recency effect also plays an important role in determining user satisfaction in search sessions. Especially, whether a user feels satisfied in the later-issued queries heavily influences his/her search satisfaction in the whole session. To take both the cascade hypothesis and the recency effect into the design of session search evaluation metrics, we propose Recency-aware Session-based Metrics (RSMs) to simultaneously characterize users' examination process with a browsing model and cognitive process with a utility accumulation model. With both self-constructed and public available user search behavior datasets, we show the effectiveness of proposed RSMs by comparing them with existing session-based metrics in the light of correlation with user satisfaction. We also find that the influence of the cascade and the recency effects varies dramatically among tasks with different difficulties and complexities, which suggests that we should use different model parameters for different types of search tasks. Our findings highlight the importance of investigating and utilizing cognitive effects besides examination hypotheses in search evaluation.

Evaluation metrics play an important role in the batch evaluation of IR systems. Based on a user model that describes how users interact with the rank list, an evaluation metric is defined to link the relevance scores of a list of documents to an estimation of system effectiveness and user satisfaction. Therefore, the validity of an evaluation metric has two facets: whether the underlying user model can accurately predict user behavior and whether the evaluation metric correlates well with user satisfaction. While a tremendous amount of work has been undertaken to design, evaluate, and compare different evaluation metrics, few studies have explored the consistency between these two facets of evaluation metrics. Specifically, we want to investigate whether the metrics that are well calibrated with user behavior data can perform as well in estimating user satisfaction. To shed light on this research question, we compare the performance of various metrics with the C/W/L Framework in estimating user satisfaction when they are optimized to fit observed user behavior. Experimental results on both self-collected and public available user search behavior datasets show that the metrics optimized to fit users' click behavior can perform as well as those calibrated with user satisfaction feedback. We also investigate the reliability in the calibration process of evaluation metrics to find out how much data is required for parameter tuning. Our findings provide empirical support for the consistency between user behavior modeling and satisfaction measurement, as well as guidance for tuning the parameters in evaluation metrics.

To provide more accurate recommendation, it is a trending topic to go beyond modeling user-item interactions and take context features into account. Factorization Machines (FM) with negative sampling is a popular solution for context-aware recommendation. However, it is not robust as sampling may lost important information and usually leads to non-optimal performances in practical. Several recent efforts have enhanced FM with deep learning architectures for modelling high-order feature interactions. While they either focus on rating prediction task only, or typically adopt the negative sampling strategy for optimizing the ranking performance. Due to the dramatic fluctuation of sampling, it is reasonable to argue that these sampling-based FM methods are still suboptimal for context-aware recommendation.

Many previous studies attempt to utilize information from other domains to achieve better performance of recommendation. Recently, social information has been shown effective in improving recommendation results with transfer learning frameworks, and the transfer part helps to learn users' preferences from both item domain and social domain. However, two vital issues have not been well-considered in existing methods: 1) Usually, a static transfer scheme is adopted to share a user's common preference between item and social domains, which is not robust in real life where the degrees of sharing and information richness are varied for different users. Hence a non-personalized transfer scheme may be insufficient and unsuccessful. 2) Most previous neural recommendation methods rely on negative sampling in training to increase computational efficiency, which makes them highly sensitive to sampling strategies and hence difficult to achieve optimal results in practical applications.

Online news streaming services have been one of the major information acquisition resources for mobile users. In many cases, users click an article but find it cannot satisfy or even annoy them. Intuitively, these negative experiences will affect users' behaviors and satisfaction, but such effects have not been well understood. In this work, a retrospective analysis is conducted using real users' log data, containing user's explicit feedback of negative experiences, from a commercial news streaming application. Through multiple intra-session comparison experiments, we find that in current session, users will spend less time reading the content, lose activeness and leave sooner after having negative experiences. Later return and significant changes of user behaviors in the next session are also observed, which demonstrates the existence of inter-session effects of negative experiences.

User behaviors are widely used as implicit feedbacks of user preferences in personalized information systems. In previous works and online applications, the user's click signals are used as positive feedback for ranking, recommendation, evaluation, etc. However, when users click on a piece of low-quality news, they are more likely to have negative experiences and different reading behaviors. Hence, the ignorance of the quality effects of news may lead to the misinterpretation of user behaviors as well as consequence studies. To address these issues, we conducted an in-depth user study in mobile news streaming scenario to investigate whether and how the quality of news may affect user preferences and user behaviors. Firstly, we verify that quality does affect user preferences, and low-quality news results in a lower preference. We further find that this effect varies with both interaction phases and user's interest in the topic of the news. Secondly, we inspect how users interact with low-quality news. Surprisingly, we find that users are more likely to click on low-quality news because of its high title persuasion. Moreover, users will read less and slower with fewer revisits and examinations while reading the low-quality news.

Explainability and effectiveness are two key aspects for building recommender systems. Prior efforts mostly focus on incorporating side information to achieve better recommendation performance. However, these methods have some weaknesses: (1) prediction of neural network-based embedding methods are hard to explain and debug; (2) symbolic, graph-based approaches (e.g., meta path-based models) require manual efforts and domain knowledge to define patterns and rules, and ignore the item association types (e.g. substitutable and complementary). In this paper, we propose a novel joint learning framework to integrate induction of explainable rules from knowledge graph with construction of a rule-guided neural recommendation model. The framework encourages two modules to complement each other in generating effective and explainable recommendation: 1) inductive rules, mined from item-centric knowledge graphs, summarize common multi-hop relational patterns for inferring different item associations and provide human-readable explanation for model prediction; 2) recommendation module can be augmented by induced rules and thus have better generalization ability dealing with the cold-start issue. Extensive experiments1 show that our proposed method has achieved significant improvements in item recommendation over baselines on real-world datasets. Our model demonstrates robust performance over “noisy” item knowledge graphs, generated by linking item names to related entities.

Repeat consumption is a common scenario in daily life, such as repurchasing items and revisiting websites, and is a critical factor to be taken into consideration for recommender systems. Temporal dynamics play important roles in modeling repeat consumption. It is noteworthy that for items with distinct lifetimes, consuming tendency for the next one fluctuates differently with time. For example, users may repurchase milk weekly, but it is possible to repurchase mobile phone after a long period of time. Therefore, how to adaptively incorporate various temporal patterns of repeat consumption into a holistic recommendation model has been a new and important problem.

Highly imbalanced data is common in the real world and it is important but difficult to train an effective classifier. In this paper, Our major point is that the imbalance is the observed phenomenon but not the cause of the problem. The challenge is that useful information is been overshadowed in the large scale of data in both majority and minority classes. We propose a novel two-step strategy, Information Accumulation, which first selects the most discriminative data by the Zooming-in phase, and then leverages unlabeled data by pseudo active learning and self-training in the phase of Learning from Learned Results. Comparative experiments are conducted on large-scale highly imbalanced real customer service data on complaint detection task (where less than 2% of data is positive). The results on eight state-of-the-art classification algorithms show that significant improvements are observed on the performances of all algorithms with Information Accumulation(for example, the F-Measure score of Xgboost is increased by 197% from 0.115 to 0.347), which demonstrates the effectiveness and general applicability of the proposed strategy. This work explores a new idea on dealing with highly imbalanced data that we do not aim to balance the training examples as usual, but focus on finding the most discriminative information from labeled data and the learning results of unlabeled data.