MoEC: Mixture of Expert Clusters
Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make experts conditionally activated. However, as the number of experts grows, MoE with outrageous parameters suffers from overfitting and sparse data allocation. Such problems are especially severe on tasks with limited data, thus hindering the progress for MoE models to improve performance by scaling up. In this work, we propose Mixture of Expert Clusters - a general approach to enable expert layers to learn more diverse and appropriate knowledge by imposing variance-based constraints on the routing stage. We further propose a cluster-level expert dropout strategy specifically designed for the expert cluster structure. Our experiments reveal that MoEC could improve performance on machine translation and natural language understanding tasks, and raise the performance upper bound for scaling up experts under limited data. We also verify that MoEC plays a positive role in mitigating overfitting and sparse data allocation.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationMixture-of-ExpertsNatural Language UnderstandingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers
Diffusion Transformers with Mixture-of-Experts (DiT-MoE) improve model capacity under sparse activation, but diffusion inference is still bottlenecked by redundant computation across timesteps. Existing caching methods m…
MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly Detection
The CLIP model's outstanding generalization has driven recent success in Zero-Shot Anomaly Detection (ZSAD) for detecting anomalies in unseen categories. The core challenge in ZSAD is to specialize the model for anomaly …
Anomaly DetectionMoECodec: Image Compression for joint human and machine perception via Mixture-of-Experts
Image compression for machines calls for a unified codec that serves multiple downstream vision tasks. Existing approaches either adopt task-specific end-to-end designs, raising parameter and deployment overhead, or rely…
Image ReconstructionImage CompressionMoEC: Mixture of Experts Implicit Neural Compression
Emerging Implicit Neural Representation (INR) is a promising data compression technique, which represents the data using the parameters of a Deep Neural Network (DNN). Existing methods manually partition a complex scene …
Data CompressionMixture-of-ExpertsMoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
The transformer architecture has become a cornerstone of modern AI, fueling remarkable progress across applications in natural language processing, computer vision, and multimodal learning. As these models continue to sc…