Review — X-MoE: On the Representation Collapse of Sparse Mixture of Experts
On the Representation Collapse of Sparse Mixture of Experts,
X-MoE, by Beijing Institute of Technology,Microsoft Corporation, and Peking University
2022 NeurIPS (Sik-Ho Tsang @ Medium)
1991 … 2022 [GPT-NeoX-20B] [GPT-3.5, InstructGPT] [GLM] [MT-NLG 530B] [Chinchilla] [PaLM] [AlexaTM] [BLOOM] [AlexaTM 20B] [OPT] [Switch Transformers] [LaMDA] [LoRA] [Galactica] [WideNet] [MoEBERT] 2023 [GPT-4] [LLaMA] [LIMA] [Koala] [BloombergGPT] [GLM-130B] [UL2]
==== My Other Paper Readings Are Also Over Here ====
- Learning a routing mechanism in Sparse MoE encourages token clustering around expert centroids, implying a trend toward representation collapse.
- In this work, X-MoE proposes to estimate the routing scores between tokens and experts on a low-dimensional hypersphere, alleviates the representation collapse issue and achieves more consistent routing than the baseline mixture-of-experts methods.
- Collapse Issue in MoE
1. Collapse Issue in MoE
- For the input token x with its hidden representation h, the router computes the routing score between h and the i-th expert by a dot-product similarity metric si = h·ei, where ei is a learnable expert embedding, and d is the hidden size of the model.
- Then, the router utilizes a sparse gating function g(r) to make the expert network conditionally activated. In this paper, authors focus on top-1 routing. Formally, considering a SMoE layer with N expert:
- where fFFNk() stands for the k-th expert network that is implemented as stacked feed-forward networks.
- For gating function g(sk), it can be softmax or sigmoid gating: