Recommendation algorithms rely on user historical interactions to deliver personalized suggestions, which raises significant privacy concerns. Federated recommendation algorithms tackle this issue by combining local model training with server-side model aggregation, where most existing algorithms use a uniform weighted summation to aggregate item embeddings from different client models. This approach has three major limitations: 1) information loss during aggregation, 2) failure to retain personalized local features, and 3) incompatibility with parameter-free recommendation algorithms. To address these limitations, we first review the development of recommendation algorithms and recognize that their core function is to share collaborative information, specifically the global relationship between users and items. With this understanding, we propose a novel aggregation paradigm named collaborative information aggregation, which focuses on sharing collaborative information rather than item parameters. Based on this new paradigm, we introduce the federated collaborative information aggregation (FedCIA) method for privacy-preserving recommendation. This method requires each client to upload item similarity matrices for aggregation, which allows clients to align their local models without constraining embeddings to a unified vector space. As a result, it mitigates information loss caused by direct summation, preserves the personalized embedding distributions of individual clients, and supports the aggregation of parameter-free models. Theoretical analysis and experimental results on real-world datasets demonstrate the superior performance of FedCIA compared with the state-of-the-art federated recommendation algorithms. Code is available at https://github.com/Mingzhe-Han/FedCIA.

Sequential recommendation methods can capture dynamic user preferences from user historical interactions to achieve better performance. However, most existing methods only use past information extracted from user historical interactions to train the models, leading to the deviations of user preference modeling. Besides past information, future information is also available during training, which contains the ''oracle'' user preferences in the future and will be beneficial to model dynamic user preferences. Therefore, we propose an oracle-guided dynamic user preference modeling method for sequential recommendation (Oracle4Rec), which leverages future information to guide model training on past information, aiming to learn ''forward-looking'' models. Specifically, Oracle4Rec first extracts past and future information through two separate encoders, then learns a forward-looking model through an oracle-guiding module which minimizes the discrepancy between past and future information. We also tailor a two-phase model training strategy to make the guiding more effective. Extensive experiments demonstrate that Oracle4Rec is superior to state-of-the-art sequential methods. Further experiments show that Oracle4Rec can be leveraged as a generic module in other sequential recommendation methods to improve their performance with a considerable margin.

Temporal recommendation methods can achieve superior accuracy due to updating user/item embeddings continuously once obtaining new interactions. However, the randomness of user behaviors will introduce noises into the user interactions and cause the deviation in the modeling of user preference, resulting in sub-optimal performance. To this end, we propose NeuFilter, a robust temporal recommendation algorithm based on neural Kalman Filtering, to learn more accurate user and item embeddings with noisy interactions. Classic Kalman Filtering is time-consuming when applied to recommendation due to its covariance matrices. Thus, we propose a neural network solution to Kalman Filtering, so as to realize higher efficiency and stronger expressivity. Specifically, NeuFilter consists of three alternating units: 1) prediction unit, which predicts user and item embeddings based on their historical embeddings; 2) estimation unit, which updates user and item embeddings in a manner similar to Kalman Filtering; 3) correction unit, which corrects the updated user and item embeddings from estimation unit to ensure reliable estimation and accurate update. Experiments on two recommendation tasks show that NeuFilter can achieve higher accuracy compared with the state-of-the-art methods, while achieving high robustness. Moreover, our empirical studies on a node classification task further confirm the importance of handling noises in tasks on temporal graph, shedding a new light on temporal graph modeling.

Graph Signal Processing (GSP) has proven to be a highly effective and efficient tool for predicting user future interactions in recommender systems. However, current GSP methods recognize user interaction patterns based on the interactions of all users, so that the recognized interaction patterns are not fully user-matched and easily impacted by other users with different interaction behaviors, resulting in sub-optimal recommendation performance. To this end, we propose a hierarchical graph signal processing method (HiGSP) for collaborative filtering, which consists of two key modules: 1) the cluster-wise filter module that recognizes user unique interaction patterns merely from interactions of users with similar preferences, making the recognized patterns able to reflect user preference without being influenced by other users with different interaction behaviors, and 2) the globally-aware filter module that serves as a complementary to the cluster-wise filter module to recognize user general interaction patterns more effectively from all user interactions. By linearly combining these two modules, HiGSP can recognize user-matched interaction patterns, so as to model user preference and predict user future interactions more accurately. Extensive experiments on six real-world datasets demonstrate the superiority of HiGSP compared to other GCN-based and GSP-based recommendation methods in terms of efficacy and efficiency.

Recommender systems are incremental in nature. Recent progresses in incremental recommendation rely on capturing the temporal dynamics of users/items from temporal interaction graphs, so that their user/item embeddings can evolve together with the graph structures. However, these methods are faced with two key challenges: 1) model training and/or updating are time-consuming and 2) new users/items cannot be effectively handled. To this end, we propose the fast incremental recommendation (FIRE) method from a graph signal processing perspective. FIRE is non-parametric which does not suffer from the time-consuming back-propagations as in previous learning-based methods, significantly improving the efficiency of model updating. In addition, we encode user/item temporal information and side information by designing new graph filters in FIRE, which can capture the temporal dynamics of users/items and address the cold-start issue for new users/items, respectively. Experimental studies on four popular datasets demonstrate that FIRE can improve the accuracy by a large margin and improve the model updating efficiency by at least 3X compared with the state-of-the-art incremental recommendation algorithms. The Code is available at https://github.com/Yaveng/FIRE.

Graph neural networks (GNN) recently achieved huge success in collaborative filtering (CF) due to the useful graph structure information. However, users will continuously interact with items, which causes the user-item interaction graphs to change over time and well-trained GNN models to be out-of-date soon. Naive solutions such as periodic retraining lose important temporal information and are computationally expensive. Recent works that leverage recurrent neural networks to keep GNN up-to-date may suffer from the "catastrophic forgetting'' issue, and experience a cold start with new users and items. To this end, we propose the incremental graph convolutional network (IGCN) --- a pure graph convolutional network (GCN) based method to update GNN models when new user-item interactions are available. IGCN consists of two main components: 1) a historical feature generation layer, which generates the initial user/item embedding via model agnostic meta-learning and ensures good initial states and fast model adaptation; 2) a temporal feature learning layer, which first aggregates the features from local neighborhood to update the embedding of each user/item within each subgraph via graph convolutional network and then fuses the user/item embeddings from last subgraph and current subgraph via incremental temporal convolutional network. Experimental studies on real-world datasets show that IGCN can outperform state-of-the-art CF algorithms in sequential recommendation tasks.