Minghua Xu
Minghua Xu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Huiyuan Chen
Case Western Reserve University
3 shared publications - Yiwei Cai
Visa Research, Austin, TX, USA
3 shared publications - Chin-Chia Michael Yeh
Visa Research, Foster City, CA, USA
2 shared publications - Vivian Lai
Visa Research, Foster City, CA, USA
2 shared publications - Hanghang Tong
University of Illinois Urbana-Champaign, Urbana, IL, USA
1 shared publication - Hao Yang
Visa Research, Palo Alto, CA, USA
1 shared publication
Latest Publications
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2502-2506
Masked Graph Transformer for Large-Scale Recommendation
Graph Transformers have garnered significant attention for learning graph-structured data, thanks to their superb ability to capture long-range dependencies among nodes. However, the quadratic space and time complexity hinders the scalability of Graph Transformers, particularly for large-scale recommendation. Here we propose an efficient Masked Graph Transformer, named MGFormer, capable of capturing all-pair interactions among nodes with a linear complexity. To achieve this, we treat all user/item nodes as independent tokens, enhance them with positional embeddings, and feed them into a kernelized attention module. Additionally, we incorporate learnable relative degree information to appropriately reweigh the attentions. Experimental results show the superior performance of our MGFormer, even with a single attention layer.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2502-2506
Open AccessMasked Graph Transformer for Large-Scale Recommendation
Graph Transformers have garnered significant attention for learning graph-structured data, thanks to their superb ability to capture long-range dependencies among nodes. However, the quadratic space and time complexity hinders the scalability of Graph Transformers, particularly for large-scale recommendation. Here we propose an efficient Masked Graph Transformer, named MGFormer, capable of capturing all-pair interactions among nodes with a linear complexity. To achieve this, we treat all user/item nodes as independent tokens, enhance them with positional embeddings, and feed them into a kernelized attention module. Additionally, we incorporate learnable relative degree information to appropriately reweigh the attentions. Experimental results show the superior performance of our MGFormer, even with a single attention layer.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1237-1248
Can One Embedding Fit All? A Multi-Interest Learning Paradigm Towards Improving User Interest Diversity Fairness
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.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1237-1248
Open AccessCan One Embedding Fit All? A Multi-Interest Learning Paradigm Towards Improving User Interest Diversity Fairness
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.
- Open Access
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1405-1414
Energy Efficient Obfuscation of Side-Channel Leakage for Preventing Side-Channel Attacks
How to efficiently prevent side-channel attacks (SCAs) on cryptographic implementations and devices has become an important problem in recent years. One of the widely used countermeasures to combat power consumption based SCAs is to inject indiscriminate random noise sequences into the raw leakage traces. However, this method leads to significant increases in the energy consumption which is unaffordable cost for battery powered devices, 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 a practical approach of energy efficient noise generation to prevent SCAs. We first take advantage of sparsity of the information in the leakage traces, and prove the existence of energy efficient noise generation that is optimized in the side channel protection under a given energy consumption budget, and also provide the optimal solution. Compared to the previous approach that also focuses on the energy efficiency, our solution is applicable to all general categories of compression methods. Furthermore, we also propose a practical noise generator design by aggregating the noise generation patterns under a variety of compression methods from different categories. As a result, the method presented in this paper is practically more applicable than previous one. The experimental results also validate the effectiveness of our proposed scheme.
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1405-1414
Open AccessEnergy Efficient Obfuscation of Side-Channel Leakage for Preventing Side-Channel Attacks
How to efficiently prevent side-channel attacks (SCAs) on cryptographic implementations and devices has become an important problem in recent years. One of the widely used countermeasures to combat power consumption based SCAs is to inject indiscriminate random noise sequences into the raw leakage traces. However, this method leads to significant increases in the energy consumption which is unaffordable cost for battery powered devices, 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 a practical approach of energy efficient noise generation to prevent SCAs. We first take advantage of sparsity of the information in the leakage traces, and prove the existence of energy efficient noise generation that is optimized in the side channel protection under a given energy consumption budget, and also provide the optimal solution. Compared to the previous approach that also focuses on the energy efficiency, our solution is applicable to all general categories of compression methods. Furthermore, we also propose a practical noise generator design by aggregating the noise generation patterns under a variety of compression methods from different categories. As a result, the method presented in this paper is practically more applicable than previous one. The experimental results also validate the effectiveness of our proposed scheme.
- Open Access
- 14 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 791-797
Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation
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 S3Rec and CL4SRec, without the need for pre-training or strong data augmentations.
- 14 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 791-797
Open AccessEnhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation
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 S3Rec and CL4SRec, without the need for pre-training or strong data augmentations.