Recommender systems (RSs) have gained widespread applications across various domains owing to the superior ability to capture users' interests. However, the complexity and nuanced nature of users' interests, which span a wide range of diversity, pose a significant challenge in delivering fair recommendations. In practice, user preferences vary significantly; some users show a clear preference toward certain item categories, while others have a broad interest in diverse ones. Even though it is expected that all users should receive high-quality recommendations, the effectiveness of RSs in catering to this disparate interest diversity remains under-explored. In this work, we investigate whether users with varied levels of interest diversity are treated fairly. Our empirical experiments reveal an inherent disparity: users with broader interests often receive lower-quality recommendations. To mitigate this, we propose a multi-interest framework that uses multiple (virtual) interest embeddings rather than single ones to represent users. Specifically, the framework consists of stacked multi-interest representation layers, which include an interest embedding generator that derives virtual interests from shared parameters, and a center embedding aggregator that facilitates multi-hop aggregation. Experiments demonstrate the effectiveness of the framework in achieving better trade-off between fairness and utility across various datasets and backbones.
Transformer and its variants are a powerful class of architectures for sequential recommendation, owing to their ability of capturing a user's dynamic interests from their past interactions. Despite their success, Transformer-based models often require the optimization of a large number of parameters, making them difficult to train from sparse data in sequential recommendation. To address the problem of data sparsity, previous studies have utilized self-supervised learning to enhance Transformers, such as pre-training embeddings from item attributes or contrastive data augmentations. However, these approaches encounter several training issues, including initialization sensitivity, manual data augmentations, and large batch-size memory bottlenecks. In this work, we investigate Transformers from the perspective of loss geometry, aiming to enhance the models' data efficiency and generalization in sequential recommendation. We observe that Transformers (e.g., SASRec) can converge to extremely sharp local minima if not adequately regularized. Inspired by the recent Sharpness-Aware Minimization (SAM), we propose SAMRec, which significantly improves the accuracy and robustness of sequential recommendation. SAMRec performs comparably to state-of-the-art self-supervised Transformers, such as S$^3$Rec and CL4SRec, without the need for pre-training or strong data augmentations.
Side-channel attacks (SCAs), which infer secret information (for example secret keys) by exploiting information that leaks from the implementation (such as power consumption), have been shown to be a non-negligible threat to modern cryptographic implementations and devices in recent years. Hence, how to prevent side-channel attacks on cryptographic devices has become an important problem. One of the widely used countermeasures to against power SCAs is the injection of random noise sequences into the raw leakage traces. However, the indiscriminate injection of random noise can lead to significant increases in energy consumption in device, and ways must be found to reduce the amount of energy in noise generation while keeping the side-channel invisible. In this paper, we propose an optimal energy-efficient design for artificial noise generation to prevent side-channel attacks. This approach exploits the sparsity among the leakage traces. We model the side-channel as a communication channel, which allows us to use channel capacity to measure the mutual information between the secret and the leakage traces. For a given energy budget in the noise generation, we obtain the optimal design of the artificial noise injection by solving the side-channel's channel capacity minimization problem. The experimental results also validate the effectiveness of our proposed scheme.