Large language models (LLM) have demonstrated remarkable capability in recommendation tasks. Recently, efforts have been made to further enhance LLM performance with collaborative knowledge learned from traditional recommender systems. One approach is to inject learned embeddings into LLM prompts through a trainable projector, yet these embeddings could carry noisy or irrelevant information. In this paper, we propose using sparse autoencoders to improve input prompts. We show that sparse autoencoders can learn highly interpretable embeddings and extract key collaborative features in the case of recommender systems. With the help of sparse autoencoders, we are able to extract collaborative features to augment input prompts. By capturing TopK features of each item, we mitigate noisy information from item embeddings, therefore sparse autoencoders can also help with denoising embeddings in prompts. We develop two methods that utilize sparse autoencoders to augment or denoise input prompts. We evaluate the proposed methods on three real-world datasets and both show promising performance improvements.

Many modern recommender systems represent user and item attributes as embedding vectors, relying on them for accurate recommendations. However, entangled embeddings often capture not only intrinsic property factors (e.g., user interest in item property) but also popularity factors (e.g., user conformity to item popularity) indistinguishably. These embeddings, influenced by popularity distribution, may face challenges when the popularity distribution at test time differs from historical distribution. Existing remedies in the literature involve disentangled embedding learning, which aims to separately capture intrinsic and popularity factors, demonstrating plausible generalization during popularity distribution shifts. However, we highlight that these methods often overlook a crucial aspect of popularity shifts-their temporal nature-in both training and inference phases. To address this, we propose Temporal Popularity distribution shift generalizABle recommender system (TPAB), a novel disentanglement framework incorporating temporal popularity. TPAB introduce a new (1) temporal-aware embedding design for users and items. Within this design, (2) popularity coarsening and (3) popularity bootstrapping are proposed to enhance generalization further. We also provide theoretical analysis showing that the bootstrapping loss eliminates the effect of popularity on the learned model. During inference, we infer test-time popularity and corresponding embeddings, using them alongside property embeddings for prediction. Extensive experiments on real-world datasets validate TPAB, showcasing its outstanding generalization ability during temporal popularity distribution shifts.

In the era of big data and AI, recommender systems must adapt to evolving user preferences and new users/items to maintain high-quality recommendations. Fine-tuning, which updates model parameters using only new data, offers an efficient alternative to full retraining but struggles to balance stability (retaining past knowledge) and plasticity (adapting to new knowledge). While existing methods prioritize stability to address catastrophic forgetting, we argue that plasticity must also be explicitly strengthened, especially for users with rapidly changing preferences. In this work, we propose PlastIcity and StAbility balancing continual recommender systems (PISA), a novel framework that adaptively balances stability and plasticity based on user preference shifts. PISA quantifies preference shifts as changes in user distances to item clusters, and then guides user embeddings by prioritizing stability for stable users and plasticity for dynamic users. To achieve this, PISA leverages backward knowledge from the previous model and forward knowledge from fine-tuning on current data. During training, PISA maximizes mutual information between user-specific parameters and the relevant reference knowledge. Theoretically, we show that enhancing plasticity mitigates distribution shifts more effectively than fine-tuning alone. Empirically, extensive experiments on three real-world datasets validate PISA's superiority over existing methods and highlight the contributions of its components.

Algorithmic fairness has been receiving increasing attention in recent years. Among others, individual fairness, with its root in the dictionary definition of fairness, offers a fine-grained fairness notion. At the algorithmic level, individual fairness can often be operationalized as a convex regularization term with respect to a similarity matrix. Appealing as it might be, a notorious challenge of individual fairness lies in how to find appropriate distance or similarity measure, which largely remains open to date. Consequently, the similarity or distance measure used in almost any individually fair algorithm is likely to be imperfect due to various reasons such as imprecise prior/domain knowledge, noise, or even adversaries. In this paper, we take an important step towards resolving this fundamental challenge and ask: how sensitive is the individually fair learning algorithm with respect to the given similarities? How can we make the learning results robust with respect to the imperfection of the given similarity measure? First (Soul-M), we develop a sensitivity measure to characterize how the learning outcomes of an individually fair learning algorithm change in response to the change of the given similarity measure. Second (Soul-A ), based on the proposed sensitive measure, we further develop a robust individually fair algorithm by adversarial learning that optimizes the similarity matrix to defend against L_∞ attack. A unique advantage of our sensitivity measure and robust algorithm lies in that they are applicable to a broad range of learning models as long as the objective function is twice differentiable. We conduct extensive experiments to demonstrate the efficacy of our methods.

User-side group fairness is crucial for modern recommender systems, alleviating performance disparities among user groups defined by sensitive attributes like gender, race, or age. In the everevolving landscape of user-item interactions, continual adaptation to newly collected data is crucial for recommender systems to stay aligned with the latest user preferences. However, we observe that such continual adaptation often worsen performance disparities. This necessitates a thorough investigation into user-side fairness in dynamic recommender systems. This problem is challenging due to distribution shifts, frequent model updates, and nondifferentiability of ranking metrics. To our knowledge, this paper presents the first principled study on ensuring user-side fairness in dynamic recommender systems. We start with theoretical analyses on fine-tuning v.s. retraining, showing that the best practice is incremental fine-tuning with restart. Guided by our theoretical analyses, we propose FAir Dynamic rEcommender (FADE), an end-to-end fine-tuning framework to dynamically ensure user-side fairness over time. To overcome the non-differentiability of recommendation metrics in the fairness loss, we further introduce Differentiable Hit (DH) as an improvement over the recent NeuralNDCG method, not only alleviating its gradient vanishing issue but also achieving higher efficiency. Besides that, we also address the instability issue of the fairness loss by leveraging the competing nature between the recommendation loss and the fairness loss. Through extensive experiments on real-world datasets, we demonstrate that FADE effectively and efficiently reduces performance disparities with little sacrifice in the overall recommendation performance.

With the prosperity of e-commerce and web applications, Recommender Systems (RecSys) have become an indispensable and important component in our daily lives, providing personalized suggestions that cater to user preferences. While Deep Neural Networks (DNNs) have achieved significant advancements in enhancing recommender systems by modeling user-item interactions and incorporating their textual side information, these DNN-based methods still exhibit some limitations, such as difficulties in effectively understanding users' interests and capturing textual side information, inabilities in generalizing to various seen/unseen recommendation scenarios and reasoning on their predictions, etc. Meanwhile, the development of Large Language Models (LLMs), such as ChatGPT and GPT-4, has revolutionized the fields of Natural Language Processing (NLP) and Artificial Intelligence (AI), due to their remarkable abilities in fundamental responsibilities of language understanding and generation, as well as impressive generalization capabilities and reasoning skills. As a result, recent studies have actively attempted to harness the power of LLMs to enhance recommender systems. Given the rapid evolution of this research direction in recommender systems, there is a pressing need for a systematic overview that summarizes existing LLM-empowered recommender systems, so as to provide researchers and practitioners in relevant fields with an in-depth understanding. Therefore, in this survey, we conduct a comprehensive review of LLM-empowered recommender systems from various aspects including pre-training, fine-tuning, and prompting paradigms. More specifically, we first introduce the representative methods to harness the power of LLMs (as a feature encoder) for learning representations of users and items. Then, we systematically review the emerging advanced techniques of LLMs for enhancing recommender systems from three paradigms, namely pre-training, fine-tuning, and prompting. Finally, we comprehensively discuss the promising future directions in this emerging field.

Despite the success of the Sylvester equation empowered methods on various graph mining applications, such as semi-supervised label learning and network alignment, there also exists several limitations. The Sylvester equation's inability of modeling non-linear relations and the inflexibility of tuning towards different tasks restrict its performance. In this paper, we propose an end-to-end neural framework, SYMGNN, which consists of a multi-network neural aggregation module and a prior multi-network association incorporation learning module. The proposed framework inherits the key ideas of the Sylvester equation, and meanwhile generalizes it to overcome aforementioned limitations. Empirical evaluations on real-world datasets show that the instantiations of SYMGNN overall outperform the baselines in geometric matrix completion task, and its low-rank instantiation could further reduce the memory consumption by 16.98% on average.

Modern recommender systems usually include separate recommendation carousels such as ‘trending now’ to list trending items and further boost their popularity, thereby attracting active users. Though widely useful, such ‘trending now’ carousels typically generate item lists based on simple heuristics, e.g., the number of interactions within a time interval, and therefore still leave much room for improvement. This paper aims to systematically study this under-explored but important problem from the new perspective of time series forecasting. We first provide a set of rigorous definitions related to item trendiness and formulate the trend recommendation task as a one-step time series forecasting problem. We then propose a deep latent variable model, dubbed Trend Recommender (TrendRec), to forecast items’ future trends and generate trending item lists. Furthermore, we design associated evaluation protocols for trend recommendation. Experiments on real-world datasets from various domains show that our TrendRec significantly outperforms the baselines, verifying our model’s effectiveness.

Sequential models are designed to learn sequential patterns in data based on the chronological order of user interactions. However, they often ignore the timestamps of these interactions. Incorporating time is crucial because many sequential patterns are time-dependent, and the model cannot make time-aware recommendations without considering time. This article demonstrates that providing a rich representation of time can significantly improve the performance of sequential models. The existing literature treats time as a one-dimensional time-series obtained by quantizing time. In this study, we propose treating time as a multi-dimensional time-series and explore representation learning methods, including a kernel based method and an embedding-based algorithm. Experiments on multiple datasets show that the inclusion of time significantly enhances the model’s performance, and multi-dimensional methods outperform the one-dimensional method by a substantial margin.