Large Language Models (LLMs) have been extensively applied in various recommendation scenarios, including bundle generation, thanks to their exceptional reasoning capabilities and comprehensive knowledge. However, exploiting large-scale LLMs for bundle generation introduces significant efficiency challenges—primarily high computational costs during fine-tuning and inference due to their massive parameterization. Knowledge Distillation (KD) offers a promising solution by transferring expertise from large teacher models to more compact student models. This study systematically investigates KD approaches for bundle generation with the goal of minimizing computational demands while preserving performance. Specifically, we explore three critical research questions: (1) how does the format of distilled knowledge impact bundle generation performance? (2) to what extent does the quantity of distilled knowledge influence the performance? and (3) how do different ways of utilizing the distilled knowledge affect the performance? To support this investigation, we propose a comprehensive KD framework that (i) progressively extracts knowledge from raw data in increasingly complex forms, i.e., frequent patterns \(\rightarrow\) formalized rules \(\rightarrow\) deep thoughts; (ii) captures varying quantities of distilled knowledge through different sampling strategies, multi-domain accumulation, and multi-format aggregation; and (iii) exploits complementary LLM adaptation techniques—in-context learning, supervised fine-tuning, and their combination—to leverage the distilled knowledge for domain-specific adaptation and enhanced efficiency in small student models. Through extensive experiments on multiple real-world datasets, we provide valuable insights into how knowledge format, quantity, and utilization methods collectively shape the performance of LLM-based bundle generation, which exhibits the significant potential of KD for more efficient yet effective LLM-based bundle generation.

Cross-Domain Sequential Recommendation (CDSR) has recently gained attention for countering data sparsity by transferring knowledge across domains.A common approach merges domain-specific sequences into cross-domain sequences, serving as bridges to connect domains.One key challenge is to correctly extract the shared knowledge among these sequences and appropriately transfer it.Most existing works directly transfer unfiltered cross-domain knowledge rather than extracting domain-invariant components and adaptively integrating them into domain-specific modelings.Another challenge lies in aligning the domain-specific and cross-domain sequences.Existing methods align these sequences based on timestamps, but this approach can cause prediction mismatches when the current tokens and their targets belong to different domains.In such cases, the domain-specific knowledge carried by the current tokens may degrade performance.To address these challenges, we propose the A-B-Cross-to-Invariant Learning Recommender (ABXI).Specifically, leveraging LoRA's effectiveness for efficient adaptation, ABXI incorporates two types of LoRAs to facilitate knowledge adaptation.First, all sequences are processed through a shared encoder that employs a domain LoRA for each sequence, thereby preserving unique domain characteristics.Next, we introduce an invariant projector that extracts domain-invariant interests from cross-domain representations, utilizing an invariant LoRA to adapt these interests into modeling each specific domain.Besides, to avoid prediction mismatches, all domain-specific sequences are aligned to match the domains of the cross-domain ground truths.

Rumor suppression is targeted at diminishing the impact of false and negative information within social networks by decreasing the prevalence of belief in such rumors among individuals, utilizing diverse strategies. Previous studies have broadly delineated rumor suppression strategies into two primary categories: targeting key nodes or edges for obstruction, and enlisting high-influence nodes to disseminate truth-related accurate information. Traditionally, employing a singular strategy involves utilizing a static algorithm throughout the rumor suppression endeavor. This method, however, encounters difficulties in adapting to fluctuating external conditions, rendering it less efficacious in the management of rumor proliferation. In response to these challenges, we introduce the concept of Adaptive Rumor Suppression (ARS), which aims to dynamically counter rumors by taking into account the nuances of propagation dynamics and the surrounding environmental context. We propose a multi-label state transition linear threshold model to more closely mirror the complex process of information diffusion across social networks. Furthermore, we advocate for a multi-round hybrid strategy that amalgamates blocking and clarification tactics to address the ARS problem within the confines of limited resource allocations. To navigate the complexities of ARS, we introduce the Hybrid Strategy of Each Round (HS-R) algorithm, which synergizes multiple strategies to effectively counter the spread of rumors. In extension, we present the Multi-Round Multi-Label (MRML) algorithm, designed to augment the efficiency of the HS-R algorithm. Experimental evaluations conducted on authentic social network datasets illustrate that our methodologies significantly outshine baseline algorithms, offering a more effective and adaptable solution to curb rumor propagation across varied environments.

Most existing bundle generation approaches fall short in generating fixed-size bundles. Furthermore, they often neglect the underlying user intents reflected by the bundles in the generation process, resulting in less intelligible bundles. This paper addresses these limitations through the exploration of two interrelated tasks, i.e., personalized bundle generation and the underlying intent inference, based on different user sessions. Inspired by the reasoning capabilities of large language models (LLMs), we propose an adaptive in-context learning paradigm, which allows LLMs to draw tailored lessons from related sessions as demonstrations, enhancing the performance on target sessions. Specifically, we first employ retrieval augmented generation to identify nearest neighbor sessions, and then carefully design prompts to guide LLMs in executing both tasks on these neighbor sessions. To tackle reliability and hallucination challenges, we further introduce (1) a self-correction strategy promoting mutual improvements of the two tasks without supervision signals and (2) an auto-feedback mechanism for adaptive supervision based on the distinct mistakes made by LLMs on different neighbor sessions. Thereby, the target session can gain customized lessons for improved performance by observing the demonstrations of its neighbor sessions. Experiments on three real-world datasets demonstrate the effectiveness of our proposed method.

With increasing frequency of high-profile privacy breaches in various online platforms, users are becoming more concerned about their privacy. And recommender system is the core component of online platforms for providing personalized service, consequently, its privacy preservation has attracted great attention. As the gold standard of privacy protection, differential privacy has been widely adopted to preserve privacy in recommender systems. However, existing differentially private recommender systems only consider static and independent interactions, so they cannot apply to sequential recommendation where behaviors are dynamic and dependent. Meanwhile, little attention has been paid on the privacy risk of sensitive user features, most of them only protect user feedbacks. In this work, we propose a novel DIfferentially Private Sequential recommendation framework with a noisy Graph Neural Network approach (denoted as DIPSGNN) to address these limitations. To the best of our knowledge, we are the first to achieve differential privacy in sequential recommendation with dependent interactions. Specifically, in DIPSGNN, we first leverage piecewise mechanism to protect sensitive user features. Then, we innovatively add calibrated noise into aggregation step of graph neural network based on aggregation perturbation mechanism. And, this noisy graph neural network can protect sequentially dependent interactions and capture user preferences simultaneously. Extensive experiments demonstrate the superiority of our method over state-of-the-art differentially private recommender systems in terms of better balance between privacy and accuracy.

Conversational recommender system (CRS) enhances the recommender system by acquiring the latest user preference through dialogues, where an agent needs to decide “whether to ask or recommend”, “which attributes to ask”, and “which items to recommend” in each round. To explore these questions, reinforcement learning is adopted in most CRS frameworks. However, existing studies somewhat ignore to consider the connection between the previous rounds and the current round of the conversation, which might lead to the lack of prior knowledge and inaccurate decisions. In this view, we propose to facilitate the connections between different rounds of conversations in a dialogue session through deep transformer-based multi-channel meta-reinforcement learning, so that the CRS agent can decide each action/decision based on previous states, actions, and their rewards. Besides, to better utilize a user’s historical preferences, we propose a more dynamic and personalized graph structure to support the conversation module and the recommendation module. Experiment results on five real-world datasets and an online evaluation with real users in an industrial environment validate the improvement of our method over the state-of-the-art approaches and the effectiveness of our designs.

Current session-based recommender systems (SBRSs) mainly focus on maximizing recommendation accuracy, while few studies have been devoted to improve diversity beyond accuracy. Meanwhile, it is unclear how the accuracy-oriented SBRSs perform in terms of diversity. In addition, the asserted “tradeoff” relationship between accuracy and diversity has been increasingly questioned in the literature. Toward the aforementioned issues, we conduct a holistic study to particularly examine the recommendation performance of representative SBRSs w.r.t. both accuracy and diversity, striving for better understanding of the diversity-related issues for SBRSs and providing guidance on designing diversified SBRSs. Particularly, for a fair and thorough comparison, we deliberately select state-of-the-art non-neural, deep neural, and diversified SBRSs by covering more scenarios with appropriate experimental setups, e.g., representative datasets, evaluation metrics, and hyper-parameter optimization technique. The source code can be obtained via github.com/qyin863/Understanding-Diversity-in-SBRSs . Our empirical results unveil that (1) non-diversified methods can also obtain satisfying performance on diversity, which can even surpass diversified ones, and (2) the relationship between accuracy and diversity is quite complex. Besides the “tradeoff” relationship, they can be positively correlated with each other, that is, having a same-trend (win–win or lose–lose) relationship, which varies across different methods and datasets. Additionally, we further identify three possible influential factors on diversity in SBRSs (i.e., granularity of item categorization, session diversity of datasets, and length of recommendation lists) and offer an intuitive guideline and a potential solution regarding learned item embeddings for more effective session-based recommendation.

Product bundling represents a prevalent marketing strategy in both offline stores and e-commerce systems. Despite its widespread use, previous studies on bundle recommendation face two significant limitations. Firstly, they rely on noisy datasets, where bundles are defined by heuristics, e.g., products co-purchased in the same session. Secondly, they target specific tasks by holding unrealistic assumptions, e.g., the availability of bundles for recommendation directly. This paper proposes to take a step back and considers the process of bundle recommendation from a holistic user experience perspective. We first construct high-quality bundle datasets with rich metadata, particularly bundle intents, through a carefully designed crowd-sourcing task. We then define a series of tasks that together, support all key steps in a typical bundle recommendation process, from bundle detection, completion and ranking, to explanation and auto-naming, whereby 19 research questions are raised correspondingly to guide the analysis. Finally, we conduct extensive experiments and analyses with representative recommendation models and large language models (LLMs), demonstrating the challenges and opportunities, especially with the emergence of LLMs. To summarize, our study contributes by introducing novel data sources, paving the way for new research avenues, and offering insights to guide product bundling in real e-commerce platforms.

Session-based recommendation, which has witnessed a booming interest recently, focuses on predicting a user’s next interested item(s) based on an anonymous session. Most existing studies adopt complex deep learning techniques (e.g., graph neural networks) for effective session-based recommendation. However, they merely address co-occurrence between items, but fail to distinguish a causality and correlation relationship. Considering the varied interpretations and characteristics of causality and correlation relationships between items, in this study, we propose a novel method denoted as CGSR by jointly modeling causality and correlation relationships between items. In particular, we construct cause, effect, and correlation graphs from sessions by simultaneously considering the false causality problem. We further design a graph neural network–based method for session-based recommendation. To conclude, we strive to explore the relationship between items from specific “causality” (directed) and “correlation” (undirected) perspectives. Extensive experiments on three datasets show that our model outperforms other state-of-the-art methods in terms of recommendation accuracy. Moreover, we further propose an explainable framework on CGSR and demonstrate the explainability of our model via case studies on an Amazon dataset.

The motivations of users to make interactions can be divided into static preference and dynamic interest. To accurately model user representations over time, recent studies in sequential recommendation utilize information propagation and evolution to mine from batches of arriving interactions. However, they ignore the fact that people are easily influenced by the recent actions of other users in the contextual scenario, and applying evolution across all historical interactions dilutes the importance of recent ones, thus failing to model the evolution of dynamic interest accurately. To address this issue, we propose a Context-Aware Pseudo-Multi-Task Recommender System (CPMR) to model the evolution in both historical and contextual scenarios by creating three representations for each user and item under different dynamics: static embedding, historical temporal states, and contextual temporal states. To dually improve the performance of temporal states evolution and incremental recommendation, we design a Pseudo-Multi-Task Learning (PMTL) paradigm by stacking the incremental single-target recommendations into one multi-target task for joint optimization. Within the PMTL paradigm, CPMR employs a shared-bottom network to conduct the evolution of temporal states across historical and contextual scenarios, as well as the fusion of them at the user-item level. In addition, CPMR incorporates one real tower for incremental predictions, and two pseudo towers dedicated to updating the respective temporal states based on new batches of interactions. Experimental results on four benchmark recommendation datasets show that CPMR consistently outperforms state-of-the-art baselines and achieves significant gains on three of them. The source code is available at https://github.com/DiMarzioBian/CPMR.

Session-based recommendation (SR) has gained increasing attention in recent years. Quite a great amount of studies have been devoted to designing complex algorithms to improve recommendation performance, where deep learning methods account for the majority. However, most of these methods are black-box ones and ignore to provide moderate explanations to facilitate users’ understanding, which thus might lead to lowered user satisfaction and reduced system revenues. Therefore, in our study, we propose a generic Reinforced Explainable framework with Knowledge graph for Session-based recommendation (i.e., REKS), which strives to improve the existing black-box SR models (denoted as non-explainable ones) with Markov decision process. In particular, we construct a knowledge graph with session behaviors and treat SR models as part of the policy network of Markov decision process. Based on our particularly designed state vector, reward strategy, and loss function, the reinforcement learning (RL)-based framework not only achieves improved recommendation accuracy, but also provides appropriate explanations at the same time. Finally, we instantiate the REKS in five representative, state-of-the-art SR models (i.e., GRU4REC, NARM, SR-GNN, GCSAN, BERT4REC), whereby extensive experiments towards these methods on four datasets demonstrate the effectiveness of our framework on both recommendation and explanation tasks.

Opinion Maximization (OM) aims at determining a small set of influential individuals, spreading the expected opinions of an object (e.g., product or individual) to their neighbors through the social relationships and eventually producing the largest opinion spread. In previous studies, once the corresponding nodes are activated, their opinions usually keep unchanged, which fails to capture the real scenarios where the opinion of each node on the object can dynamically change over time. In this view, we propose a Dynamic Opinion Maximization Framework (DOMF) to settle the OM problem, which consists of two parts: dynamic opinion formation and adaptive seeding process. Specifically, we formulate the OM problem by maximizing rational opinions, and prove that: 1) the OM problem within a constant ratio is NP-hard, and 2) the objective function does not satisfy the monotonicity and submodularity properties anymore. To model the dynamic opinion issue, we propose adaptive cooperation model based on Q-learning theory, which is proved to be capable of eventually reaching convergence. Moreover, to dynamically generate the initial seed nodes, we design the Multi-stage Heuristic Algorithm (MHA). Experimental results demonstrate that each component of our model is effective, and the proposed approach improves the rational opinion spread.

Product bundling is a commonly-used marketing strategy in both offline retailers and online e-commerce systems. Current research on bundle recommendation is limited by: (1) noisy datasets, where bundles are defined by heuristics, e.g., products co-purchased in the same session; and (2) specific tasks, holding unrealistic assumptions, e.g., the availability of bundles for recommendation directly. In this paper, we propose to take a step back and consider the process of bundle recommendation from a holistic user experience perspective. We first construct high-quality bundle datasets with rich meta information, particularly bundle intents, through a carefully designed crowd-sourcing task. We then define a series of tasks that together, support all key steps in a typical bundle recommendation process, from bundle detection, completion, ranking, to explanation and auto-naming. Finally, we conduct extensive experiments and in-depth analysis that demonstrate the challenges of bundle recommendation, arising from the need for capturing complex relations among users, products, and bundles, as well as the research opportunities, especially in graph-based neural methods. To sum up, our study delivers new data sources, opens up new research directions, and provides useful guidance for product bundling in real e-commerce platforms. Our datasets are available at GitHub (\urlhttps://github.com/BundleRec/bundle_recommendation ).

With tremendous amount of recommendation algorithms proposed every year, one critical issue has attracted a considerable amount of attention: there are no effective benchmarks for evaluation, which leads to two major concerns, i.e., unreproducible evaluation and unfair comparison. This paper aims to conduct rigorous (i.e., reproducible and fair) evaluation for implicit-feedback based top-N recommendation algorithms. We first systematically review 85 recommendation papers published at eight top-tier conferences (e.g., RecSys, SIGIR) to summarize important evaluation factors, e.g., data splitting and parameter tuning strategies, etc. Through a holistic empirical study, the impacts of different factors on recommendation performance are then analyzed in-depth. Following that, we create benchmarks with standardized procedures and provide the performance of seven well-tuned state-of-the-arts across six metrics on six widely-used datasets as a reference for later study. Additionally, we release a user-friendly Python toolkit, which differs from existing ones in addressing the broad scope of rigorous evaluation for recommendation. Overall, our work sheds light on the issues in recommendation evaluation and lays the foundation for further investigation. Our code and datasets are available at GitHub (https://github.com/AmazingDD/daisyRec).

In the field of sequential recommendation, deep learning--(DL) based methods have received a lot of attention in the past few years and surpassed traditional models such as Markov chain-based and factorization-based ones. However, there is little systematic study on DL-based methods, especially regarding how to design an effective DL model for sequential recommendation. In this view, this survey focuses on DL-based sequential recommender systems by taking the aforementioned issues into consideration. Specifically, we illustrate the concept of sequential recommendation, propose a categorization of existing algorithms in terms of three types of behavioral sequences, summarize the key factors affecting the performance of DL-based models, and conduct corresponding evaluations to showcase and demonstrate the effects of these factors. We conclude this survey by systematically outlining future directions and challenges in this field.