Graph-based social recommendation leverages both the interaction graph and the social graph to model user preferences, especially under sparse feedback. However, users' intricate social behaviors may introduce mismatched social ties that contaminate user representations and harm the models' robustness. The majority of existing methods mitigate this by pruning, rewiring, or assigning edge-wise weights before social aggregation. From users' historical behaviors, we observe that a social neighbor often overlaps with the target user on specific interests but differs in others. Thus, using a single weight for each social connection is insufficient, as it only scales the overall message intensity and fails to selectively suppress the misaligned components within the aggregated message. To fill this gap, we propose Orthogonal Decomposition for Social Recommendation (ODSR), an embedding-space framework that orthogonally decomposes the aggregated social message into an aligned component and an orthogonal deviation, and learns a dimension-wise vector gate to regulate the deviation under ranking supervision. Additionally, we introduce a contrastive regularizer that perturbs representations along deviation directions to enhance robustness against imperfect social signals. Extensive experiments on three datasets show that ODSR consistently outperforms strong baselines, and additional analyses verify the effectiveness of selectively gating the orthogonal deviation.
Rongfeng Guo, Yinxuan Huang, Wei Chen et al.· Proceedings of the 32nd ACM...· 0 citations
Class imbalance is a significant challenge in many practical classification tasks, particularly in federated learning (FL), where both global data imbalance and local data heterogeneity across clients worsen the problem. Addressing the class imbalance problem effectively while adhering to privacy constraints remains a formidable challenge. A common solution is to rebalance (or reweight) the samples of different classes; however, the rebalancing ratio largely depends on empirical results. In this study, we propose an analytical class rebalancing method to compute the optimal rebalancing ratios for imbalanced datasets. We first theoretically derive the relationship between evaluation metrics--such as macro-precision, macro-recall, and macro-F1--and the rebalancing ratio. Based on these findings, we devise an efficient algorithm to determine the optimal rebalancing ratio that maximizes the corresponding metrics. Our method is parameter-free and doesn't increase the complexity of existing neural models. We demonstrate that our method achieves the optimum ratio for maximizing the concerned metrics while maintaining low computational complexity, scaling linearly with both the number of clients and samples. Experimental results on different datasets validate the effectiveness of our algorithms. To the best of our knowledge, we are the first to provide an analytical and parameter-free solution to the problem.
Sihao Lv, Zian Le, Mingyang Zhou et al.· Proceedings of the 32nd ACM...· 0 citations