Learning More Generalized Experts by Merging Experts in Mixture-of-Experts
This addresses a specific issue in deep learning for multi-domain incremental learning, but appears incremental as it builds on existing mixture-of-experts methods.
The paper tackles performance degradation from shared layers in mixture-of-experts by merging frequently selected experts and updating others, resulting in improved transfer learning and reduced catastrophic forgetting in multi-domain incremental learning.
We observe that incorporating a shared layer in a mixture-of-experts can lead to performance degradation. This leads us to hypothesize that learning shared features poses challenges in deep learning, potentially caused by the same feature being learned as various different features. To address this issue, we track each expert's usage frequency and merge the two most frequently selected experts. We then update the least frequently selected expert using the combination of experts. This approach, combined with the subsequent learning of the router's expert selection, allows the model to determine if the most frequently selected experts have learned the same feature differently. If they have, the combined expert can be further trained to learn a more general feature. Consequently, our algorithm enhances transfer learning and mitigates catastrophic forgetting when applied to multi-domain task incremental learning.