Federated recommender systems enable collaborative model training while keeping user interaction data local and sharing only essential model parameters, thereby mitigating privacy risks. However, existing methods overlook a critical issue, i.e., the stable learning of a generalized item embedding throughout the federated recommender system training process. Item embedding plays a central role in facilitating knowledge sharing across clients. Yet, under the cross-device setting, local data distributions exhibit significant heterogeneity and sparsity, exacerbating the difficulty of learning generalized embeddings. These factors make the stable learning of generalized item embeddings both indispensable for effective federated recommendation and inherently difficult to achieve. To fill this gap, we propose a new federated recommendation framework, named Federated Recommendation with Generalized Embedding Learning (FedRecGEL). We reformulate the federated recommendation problem from an item-centered perspective and cast it as a multi-task learning problem, aiming to learn generalized embeddings throughout the training procedure. Based on theoretical analysis, we employ sharpness-aware minimization to address the generalization problem, thereby stabilizing the training process and enhancing recommendation performance. Extensive experiments on four datasets demonstrate the effectiveness of FedRecGEL in significantly improving federated recommendation performance. Our code is available at https://github.com/anonymifish/FedRecGEL.
论文检索
输入标题、作者或关键词，从 15,207 篇学术成果中精准定位
User-centric recommendation has become essential for delivering personalized services, as it enables systems to adapt to users' evolving behaviors while respecting their long-term preferences and privacy constraints. Although federated learning offers a promising alternative to centralized training, existing approaches largely overlook user behavior dynamics, leading to temporal forgetting and weakened collaborative personalization. In this work, we propose FCUCR, a federated continual recommendation framework designed to support long-term personalization in a privacy-preserving manner. To address temporal forgetting, we introduce a time-aware self-distillation strategy that implicitly retains historical preferences during local model updates. To tackle collaborative personalization under heterogeneous user data, we design an inter-user prototype transfer mechanism that enriches each client's representation using knowledge from similar users while preserving individual decision logic. Extensive experiments on four public benchmarks demonstrate the superior effectiveness of our approach, along with strong compatibility and practical applicability. Code is available at https://github.com/Poizoner/code4FCUCR_www2026.
Federated Recommendation (FR) has emerged as a promising paradigm for addressing the learn-to-rank problem in a privacy-preserving manner. However, effectively incorporating multimodal item features into FR remains an open challenge, due to efficiency constraints, distribution heterogeneity, and feature utilization alignment with the recommendation objective. To tackle these issues, we propose GFMFR, a novel multimodal fusion framework for federated recommendation. Specifically, multimodal representation learning is offloaded to the server, which stores item content and employs a high-capacity encoder to generate expressive representations, thereby alleviating the computational burden on clients. In addition, a group-aware multimodal aggregation mechanism learns shared representations for users with similar interests, enabling knowledge sharing while alleviating distribution heterogeneity. Finally, GFMFR adopts a preference-guided distillation strategy that leverages multimodal information in a way directly aligned with recommendation objectives. The proposed framework can be seamlessly integrated into existing federated recommender systems, enhancing their effectiveness by incorporating multimodal features. Extensive experiments on five benchmark datasets demonstrate that GFMFR consistently outperforms state-of-the-art multimodal FR baselines. The implementation code is available. https://github.com/Zhangwp2420/GFMFR.
In real-world scenarios, users tend to engage with a small set of popular items, while a large number of long-tail items receive little to no interaction. This long-tail phenomenon substantially impairs recommendation quality. Although prior approaches have attempted to address this issue, the absence of sufficient collaborative signals remains a major obstacle. With the advent of Large Language Models (LLMs), recent studies have explored leveraging LLM-derived semantics to enrich recommendation models. These approaches aim to incorporate textual or contextual knowledge to compensate for limited user-item interactions. A key challenge, however, lies in effectively integrating semantic signals with collaborative representations, which originate from different modalities and learning dynamics. To tackle this, We propose a novel framework, called FCRLLM (the Flipped Classroom with LLM), for long-tail sequential recommendation that aligns collaborative and LLM-based semantic representations. The flipped classroom mechanism dynamically updates the teacher representation to align with the student's attention, enabling more effective integration of semantic and collaborative information. This alignment is implemented via an energy-based formulation inspired by Hopfield networks. To validate its effectiveness, we conduct extensive experiments on three real-world datasets and demonstrate that FCRLLM consistently improves recommendation performance regardless of item popularity or user activity.
Human mobility prediction is crucial for applications ranging from location-based recommendations to urban planning, which aims to forecast users' next location visits based on historical trajectories. While existing mobility prediction models excel at capturing sequential patterns through diverse architectures for different scenarios, they are hindered by the long-tailed distribution of location visits, leading to biased predictions and limited applicability. This highlights the need for a solution that enhances the long-tailed prediction capabilities of these models with broad compatibility and efficiency across diverse architectures. To address this need, we propose the first architecture-agnostic plugin for long-tailed human mobility prediction, named Adaptive LO cation HierArchy learning (ALOHA). Inspired by Maslow's theory of human motivation, we exploit and explore common mobility knowledge of head and tail locations derived from human mobility trajectories to effectively mitigate long-tailed bias. Specifically, we introduce an automatic pipeline to construct city-tailored location hierarchies based on Large Language Models (LLMs) and Chain-of-Thought (CoT) prompts, capturing high-level mobility semantics with minimal human verification. We further design an Adaptive Hierarchical Loss (AHL) that rebalances learning through Gumbel disturbance and node-wise adaptive weighting, enabling both exploitation of multi-level signals and exploration within semantically related groups. Extensive experiments across multiple state-of-the-art models demonstrate that ALOHA consistently improves long-tailed mobility prediction performance by up to 16.59% while maintaining efficiency and robustness. Our code is at https://github.com/Star607/ALOHA.
Rapid development of web services has led to an explosion of multimodal content, making multimodal recommender systems (MRSs) vital tools for mitigating information overload. Current MRSs have achieved remarkable progress by incorporating advanced technologies such as Graph Neural Networks (GNNs) and Large Language Models (LLMs). However, these studies still suffer from the semantic shift problem. Generally, item's multimodal content usually contain multiple objects, including target object (core content of item) and auxiliary objects (decorations of item). Existing MRSs overlooked this distinction, failing to prevent auxiliary objects from dominating the representation, leading to biased item representation. To address this issue, we propose a model-agnostic framework ''TargetMR''. Concretely, TargetMR comprises two core modules, including Object Disentangler and Object Identifier. The Object Disentangler decouples item text and image into multiple objects via text syntactic parsing and image segmentation. The Object Identifier performs knowledge distillation based on LLMs to efficiently identify the target text object. It then identifies the target image object through cross-modal semantic evaluation. Moreover, this module refines the representation of image target object by optimizing the semantic correlation. Owing to the model-agnostic design of TargetMR, it can be integrated into various backbone MRSs. Extensive experiments on three benchmark datasets show that TargetMR consistently improves the performance of five backbone MRSs, with an average improvement of 12.26%. Our codes are available at https://github.com/gutang-97/TargetMR/.
Click-through rate (CTR) prediction is a fundamental task in modern recommender systems. In recent years, the integration of large language models (LLMs) has been shown to effectively enhance the performance of traditional CTR methods. However, existing LLM-enhanced methods often require extensive processing of detailed textual descriptions for large-scale instances or user/item entities, leading to substantial computational overhead. To address this challenge, this work introduces LLaCTR, a novel and lightweight LLM-enhanced CTR method that employs a field-level enhancement paradigm. Specifically, LLaCTR first utilizes LLMs to distill crucial and lightweight semantic knowledge from small-scale feature fields through self-supervised field-feature fine-tuning. Subsequently, it leverages this field-level semantic knowledge to enhance both feature representation and feature interactions. In our experiments, we integrate LLaCTR with six representative CTR models across four datasets, demonstrating its superior performance in terms of both effectiveness and efficiency compared to existing LLM-enhanced methods. Our code is available at https://github.com/istarryn/LLaCTR.
Cross-Domain Sequential Recommendation (CDSR) seeks to improve user preference modeling by transferring knowledge from multiple domains. Despite the progress made in CDSR, most existing methods rely on overlapping users or items to establish cross-domain correlations-a requirement that rarely holds in real-world settings. The advent of large language models (LLM) and model-merging techniques appears to overcome this limitation by unifying multi-domain data without explicit overlaps. Yet, our empirical study shows that naively training an LLM on combined domains—or simply merging several domain-specific LLMs—often degrades performance relative to a model trained solely on the target domain. To address these challenges, we first experimentally investigate the cause of suboptimal performance in LLM-based cross-domain recommendation and model merging. Building on these insights, we introduce WeaveRec, which cross-trains multiple LoRA modules with source and target domain data in a ''weaving'' fashion, and fuses them via model merging. WeaveRec can be extended to multi-source domain scenarios and notably does not introduce additional inference-time cost in terms of latency or memory. Furthermore, we provide a theoretical guarantee that WeaveRec can reduce the upper bound of the expected error in the target domain. Extensive experiments on single-source, multi-source, and cross-platform cross-domain recommendation scenarios validate that WeaveRec effectively mitigates performance degradation and consistently outperforms baseline approaches in real?world recommendation tasks. Codes are available at https://github.com/mertell/WeaveRec.
Large language models (LLMs) have emerged as a promising paradigm for recommender systems, due to their powerful capabilities in global knowledge integration and reasoning. However, LLMs are inherently prone to confirmation bias -- the tendency to favor information that reinforces users' existing views -- which leads to an overemphasis on previously shown viewpoints and ignores diverse user beliefs for recommendations. To address this issue, in this paper, we propose SCoTRec, a social chain-of-thought reasoning framework for recommendation. SCoTRec first constructs sentiment-aware user profiles by extracting sentiment terms from user reviews. It then incorporates users' social sentiment information into the social chain-of-thought reasoning units to improve recommendations. In particular, we categorize the social chain-of-thought into sentiment-based pathways and apply human evaluation operations -- backtracking, discarding, retaining, and aggregating -- to simulate nuanced sentiment cognition and interpersonal influence, effectively alleviating confirmation bias. Extensive experiments on four benchmark datasets demonstrate the effectiveness of SCoTRec in alleviating confirmation bias and improving recommendations.
Federated cross-domain recommendation (Federated CDR) aims to collaboratively learn personalized recommendation models across heterogeneous domains while preserving data privacy. Recently, large language model (LLM)-based recommendation models have demonstrated impressive performance by leveraging LLMs' strong reasoning capabilities and broad knowledge. However, adopting LLM-based recommendation models in Federated CDR scenarios introduces new challenges. First, there exists a risk of overfitting with domain-specific local adapters. The magnitudes of locally optimized parameter updates often vary across domains, causing biased aggregation and overfitting toward domain-specific distributions. Second, unlike traditional recommendation models (e.g., collaborative filtering, bipartite graph-based methods) that learn explicit and comparable user/item representations, LLMs encode knowledge implicitly through autoregressive text generation training. This poses additional challenges for effectively measuring the cross-domain similarities under heterogeneity. To address these challenges, we propose an LLM-based framework for federated cross-domain recommendation, FeDecider. Specifically, FeDecider tackles the challenge of scale-specific noise by disentangling each client's low-rank updates and sharing only their directional components. To handle the need for flexible and effective integration, each client further learns personalized weights that achieve the data-aware integration of updates from other domains. Extensive experiments across diverse datasets validate the effectiveness of our proposed FeDecider.
Federated recommendation systems (FRSs) have recently gained widespread attention due to their ability to train collaborative recommendation models without exchanging raw user data. However, existing FRSs face a severe challenge of data sparsity, which manifests at both the user and item levels. First, user data sparsity: some users may only have a small number of interactions with items, struggling to adequately train the personalized user embedding locally. Second, item data sparsity: some items may only receive a small number of user ratings, causing the global model to lack knowledge about them. Considering these, we propose the Knowledge Enhanced Federated Recommendation System named as KE-FedRS, of which the core idea is to enhance the knowledge of users with few interactions and items with few ratings at both the local and global levels. Specifically, at the local level, we introduce an auxiliary user embedding and average and aggregate this auxiliary embedding across similar users, thereby enriching the knowledge of the local user embedding. At the global level, we propose a hybrid client selection strategy based on item embedding discrepancies, prioritizing clients that exhibit greater divergence in item embeddings from others, thus enhancing the knowledge of items with fewer interactions in the global model. We conduct comprehensive experiments on four real-world datasets, and the results show that the proposed method consistently outperforms baseline approaches in terms of HR@10 and NDCG@10.
Existing LLM-driven recommendation systems (RS) suffer from over-reliance on a single pre-trained model, which limits adaptability across diverse scenarios due to differences in large language models' strengths in semantics, knowledge, and reasoning. To address this issue, we propose AMLrec (Adaptive Multi-LLM Recommendation), a dynamic routing-based adaptive multi-LLM collaboration framework that unifies two dominant paradigms—LLM as Recommender and LLM + Recommender—through decision knowledge complementation. For each user or item, a lightweight encoder generates embeddings that are compared with learnable LLM prototypes using cosine similarity to select the most suitable models. In the first paradigm, selected LLMs generate recommendations via structured prompts, and their outputs are aggregated to form the final recommendation list. In the second paradigm, chosen LLMs produce semantic embeddings, which are fused with learnable embeddings after PCA-based dimensionality reduction and aligned using a lightweight adapter to bridge distribution gaps. Notably, AMLrec does not require fine-tuning of the underlying LLMs, significantly reducing computational overhead. Experiments on real-world datasets demonstrate that the proposed approach consistently outperforms single-LLM baselines across all evaluation metrics, validating its effectiveness. The main contributions of this work are threefold: introducing dynamic routing for multi-LLM recommendation system collaboration, proposing a unified architecture that harmonizes both paradigms, and enabling efficient adaptation without LLM fine-tuning. The code is available at https://github.com/Jiale-12138/AMLrec.
Search and Recommendation (S&R) are core information access channels on modern multi-scenario platforms. Existing joint S&R models face two critical challenges: (1) cross-scenario interest inconsistency, failing to unify explicit search intent (queries) and implicit recommendation intent (behavioral interactions) into coherent user interest representations; (2) severe S&R trade-off, where enhancing one task degrades the other due to static knowledge sharing and unbalanced feature utilization. To address these issues, we propose MinSAR , a novel framework focusing on cross-S&R user interest consistency. It integrates two key innovations: a Unified Interest Generation (UIG) module using Vector Quantized-Variational Autoencoder (VQ-VAE) to fuse long-term user preferences (via a user-specific memory network) and dynamic short-term contextual behaviors, generating compact cross-scenario latent representations that bridge explicit and implicit intents. Additionally, an Interest-Guided Attention Expert Network replaces static multi-task gating with intent-aware weight allocation. Guided by UIG's unified interest, it dynamically balances cross-S&R shared knowledge and task-specific expertise (semantic matching for search, collaborative filtering for recommendation), mitigating inter-task conflicts. Extensive experiments on two real-world datasets (KuaiSAR and Amazon Kindle Store) against 13 baselines show MinSAR outperforms state-of-the-art joint S&R models. Further analysis confirms its ability to eliminate the S&R performance trade-off.
Graph-based social recommendation (SocialRec) has emerged as a powerful extension of graph collaborative filtering (GCF), which leverages graph neural networks (GNNs) to capture multi-hop collaborative signals from user-item interactions. These methods enrich user representations by incorporating social network information into GCF, thereby integrating additional collaborative signals from social relations. However, existing GCF and graph-based SocialRec approaches face significant challenges: they incur high computational costs and suffer from limited scalability due to the large number of parameters required to assign explicit embeddings to all users and items. In this work, we propose PULSE (Parameter-efficient User representation Learning with Social Knowledge), a framework that addresses this limitation by constructing user representations from socially meaningful signals without creating an explicit learnable embedding for each user. PULSE reduces the parameter size by up to 50% compared to the most lightweight GCF baseline. Beyond parameter efficiency, our method achieves state-of-the-art performance, outperforming 13 GCF and graph-based social recommendation baselines across varying levels of interaction sparsity, from cold-start to highly active users, through a time- and memory-efficient modeling process.
By allowing each client to refer to the knowledge from other clients while retaining their specific characteristics, partial knowledge sharing has become one of the main approaches to realizing personalized federated learning (pFL). Representative techniques of partial knowledge sharing propose sharing the feature extractor while customizing the classifier head of the neural network. Although such methods achieve great success, the underlying principle behind them remains yet to be comprehensively understood. A fundamental problem is whether it is really appropriate to fully share the feature extractor. Based on the theory of neural collapse, in this paper, we demonstrate both theoretically and empirically that the feature extractor should be partially shared rather than fully shared. More specifically, we identify a substantial inconsistency between the fused global feature representations and expected local feature representations, and thus it is necessary to preserve partially customized layers of the feature extractor for enhancing personalized representations. Based on this discovery, we further propose a novel method called pFedDKS which detaches the shared global knowledge and customized local knowledge by providing detached feature prototypes. Extensive experiments on various datasets and models show that pFedDKS outperforms state-of-the-arts.
Sequential recommendation (SR) learns user preferences based on their historical interaction sequences and provides personalized suggestions. In real-world scenarios, most users can only interact with a handful of items, while the majority of items are seldom consumed. This pervasive long-tail challenge limits the model's ability to learn user preferences. Despite previous efforts to enrich tail items/users with knowledge from head parts or improve tail learning through additional contextual information, they still face the following issues: 1) They struggle to improve the situation where interactions of tail users/items are scarce, leading to incomplete preferences learning for the tail parts. 2) Existing methods often degrade overall or head parts performance when improving accuracy for tail users/items, thereby harming the user experience. In this work, we propose Tail-Aware Data Augmentation (TADA) for long-tail sequential recommendation, which enhances the interaction frequency for tail items/users while maintaining head performance, thereby promoting the model's learning capabilities for the tail. Specifically, we first capture the co-occurrence and correlation among low-popularity items by a linear model. Building upon this, we design two tail-aware augmentation operators, T-Substitute and T-Insert. The former replaces the head item with a relevant item, while the latter utilizes co-occurrence relationships to extend the original sequence by incorporating both head and tail items. The augmented and original sequences are mixed at the representation level to preserve preference knowledge. We further extend the mix operation across different tail-user sequences and augmented sequences to generate richer augmented samples, thereby improving tail performance. Comprehensive experiments demonstrate the superiority of our method. The codes are provided at https://github.com/KingGugu/TADA.
Conversational recommender systems (CRSs) aim to provide real-time recommendations through dynamic interactions between users and the system. Recent studies have revealed the value of personalized information derived from users' historical dialogue records in refining user preferences. However, existing methods often utilize the entire historical dialogue of a user indiscriminately, leading to the issue of cognitive negative transfer, wherein historical dialogue sessions impede rather than facilitate current decision-making. This ultimately degrades the performance of conversational recommendations. To address this issue, inspired by the behavioral decision theory, this paper proposes a novel model, Personalization-Driven Agent Debate for Conversational Recommendation, named EyeCRS. EyeCRS is comprised of two core components: (i) The Multi-Agent Debate Module employs supporting and opposing agents to simulate a human-like debate process, thereby enabling a rigorous evaluation of whether historical dialogue sessions may introduce cognitive negative transfer into the recommender. (ii) The Parametric Injection Module, subsequently, parameterizes the historical dialogues that are validated as positive and injects them into the intrinsic parameter space of the downstream recommender, thereby effectively enhancing the model's ability to internalize and utilize personalized knowledge. Experimental results on two real-world datasets show that EyeCRS effectively mitigates cognitive negative transfer and achieves superior performance in conversational recommendation.
Recently, knowledge graphs have been utilised in recommendation systems to improve accuracy by integrating item-side auxiliary information. However, structural user-side knowledge is difficult to construct and integrate due to inherent scarcity and improper granularity. This paper introduces a graph contrastive learning with Semantic transitions-Enhanced DIffusion architecture based on Large Language Models (LLMs) for user-side knowledge-aware Recommendation (SEDIRec). Specifically, our SEDIRec first leverages LLMs to infer user interests from historical behaviors, integrating this user-side information with item-side and collaborative data to construct main views. Then, two contrastive views are generated using diffusion models with semantic transitions: one at the user-side level and the other at the item-side level. For both contrastive views, we integrate user-side or item-side information with collaborative data to generate a user-item graph. Subsequently, each user-item graph is transformed into collaborative data spaces via diffusion models for generating contrastive views. This procedure not only enhances the alignment between user/item-side information and the semantic spaces of collaborative data but also effectively eliminates noise. Extensive experiments on three datasets reveal the superiority of SEDIRec, especially for users with sparse interactions.
Federated Learning (FL) enables knowledge sharing across client models with privacy preservation. A key challenge in FL is to aggregate general knowledge across clients while preserving personalized knowledge for each client. We discover that this challenge primarily stems from the coupling of general and personalized knowledge across different model layers. Existing methods either fail to fully decouple these two types of knowledge or do not leverage them effectively for inference, leading to suboptimal performance. This paper presents Thorki, a new FL system that decouples general and personalized knowledge throughout all model layers. In Thorki, instead of one model, each client stores its personalized knowledge in a small model and general knowledge in a large model. When making an inference, it employs a fusion network to combine the outputs of the two models, leveraging both types of knowledge adaptively. This new model collaboration paradigm allows clients to share their general knowledge in a federated manner without compromising their personalized inference capabilities. Extensive experiments with three models on four datasets demonstrate that Thorki outperforms state-of-the-art FL systems by 0.16%-19.14% in model accuracy and improves time-to-accuracy performance by 2.00x-10.00x.
Optimizing recommender systems for objectives beyond accuracy, such as diversity, novelty, and personalization, is crucial for long-term user satisfaction. To this end, the industry has accumulated vast amounts of structured domain knowledge, which we term human priors (e.g., item taxonomies, temporal patterns). This knowledge is typically applied through post-hoc adjustments during ranking or post-ranking. However, this approach remains decoupled from the core model learning, which is particularly undesirable as the industry shifts to end-to-end generative recommendation foundation models. On the other hand, many methods targeting these beyond-accuracy objectives often require architecture-specific modifications and discard these valuable human priors by learning user intent in a fully unsupervised manner. Instead of discarding the human priors accumulated over years of practice, we introduce a backbone-agnostic framework that seamlessly integrates these human priors directly into the end-to-end training of generative recommenders. With lightweight, prior-conditioned adapter heads inspired by efficient LLM decoding strategies, our approach guides the model to disentangle user intent along human-understandable axes (e.g., interaction types, long- vs. short-term interests). We also introduce a hierarchical composition strategy for modeling complex interactions across different prior types. Extensive experiments on three large-scale datasets demonstrate that our method significantly enhances both accuracy and beyond-accuracy objectives. We also show that human priors allow the backbone model to more effectively leverage longer context lengths and larger model sizes.