1.9k citations · 10.4k across the 198 of their papers we have counts for
6 papers · 1 filter
Are More Layers Beneficial to Graph Transformers?
Haiteng Zhao, Shuming Ma, Dongdong Zhang +2
Despite that going deep has proven successful in many neural architectures, the existing graph transformers are relatively shallow. In this work, we explore whether more layers are…
TorchScale: Transformers at Scale
Shuming Ma, Hongyu Wang, Shaohan Huang +8
Large Transformers have achieved state-of-the-art performance across many tasks. Most open-source libraries on scaling Transformers focus on improving training or inference with be…
Foundation Transformers
Hongyu Wang, Shuming Ma, Shaohan Huang +12
A big convergence of model architectures across language, vision, speech, and multimodal is emerging. However, under the same name "Transformers", the above areas use different imp…
Task-Specific Expert Pruning for Sparse Mixture-of-Experts
Tianyu Chen, Shaohan Huang, Yuan Xie +5
The sparse Mixture-of-Experts (MoE) model is powerful for large-scale pre-training and has achieved promising results due to its model capacity. However, with trillions of paramete…
StableMoE: Stable Routing Strategy for Mixture of Experts
Damai Dai, Li Dong, Shuming Ma +4
The Mixture-of-Experts (MoE) technique can scale up the model size of Transformers with an affordable computational overhead. We point out that existing learning-to-route MoE metho…
Memory-Efficient Differentiable Transformer Architecture Search
Yuekai Zhao, Li Dong, Yelong Shen +3
Differentiable architecture search (DARTS) is successfully applied in many vision tasks. However, directly using DARTS for Transformers is memory-intensive, which renders the searc…