58 citations · 107 across the 8 of their papers we have counts for
8 papers
Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts
Weilin Cai, Juyong Jiang, Le Qin +3
Expert parallelism has emerged as a key strategy for distributing the computational workload of sparsely-gated mixture-of-experts (MoE) models across multiple devices, enabling the…
Feature-Balanced Loss for Long-Tailed Visual Recognition
Mengke Li, Yiu-ming Cheung, Juyong Jiang
Deep neural networks frequently suffer from performance degradation when the training data is long-tailed because several majority classes dominate the training, resulting in a bia…
Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting
Juyong Jiang, Binqing Wu, Ling Chen +2
Traffic forecasting is an essential problem in urban planning and computing. The complex dynamic spatial-temporal dependencies among traffic objects (e.g., sensors and road segment…
Compact Neural Networks via Stacking Designed Basic Units
Weichao Lan, Yiu-ming Cheung, Juyong Jiang
Unstructured pruning has the limitation of dealing with the sparse and irregular weights. By contrast, structured pruning can help eliminate this drawback but it requires complex c…
AdaMCT: Adaptive Mixture of CNN-Transformer for Sequential Recommendation
Juyong Jiang, Peiyan Zhang, Yingtao Luo +6
Sequential recommendation (SR) aims to model users dynamic preferences from a series of interactions. A pivotal challenge in user modeling for SR lies in the inherent variability o…
Vertical Federated Principal Component Analysis and Its Kernel Extension on Feature-wise Distributed Data
Yiu-ming Cheung, Juyong Jiang, Feng Yu +1
Despite enormous research interest and rapid application of federated learning (FL) to various areas, existing studies mostly focus on supervised federated learning under the horiz…
Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-training
Juyong Jiang, Peiyan Zhang, Yingtao Luo +6
Sequential recommendation systems are integral to discerning temporal user preferences. Yet, the task of learning from abbreviated user interaction sequences poses a notable challe…
Cascaded Semantic and Positional Self-Attention Network for Document Classification
Juyong Jiang, Jie Zhang, Kai Zhang
Transformers have shown great success in learning representations for language modelling. However, an open challenge still remains on how to systematically aggregate semantic infor…