Pith. sign in

REVIEW 4 cited by

Learning More Generalized Experts by Merging Experts in Mixture-of-Experts

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.11530 v1 pith:DZZFWDJ2 submitted 2024-05-19 cs.LG

classification cs.LG
keywords learningexpertsexpertfeaturefrequentlyselectedcombinedfeatures
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Expert Routing with Synthetic Data for Continual Learning

    cs.LG 2024-12 conditional novelty 7.0 of 10

    G2D trains a domain discriminator on synthetic data to route test samples to domain-specific experts, outperforming generative replay on several continual learning benchmarks.

  2. ResidualDroppath: Enhancing Feature Reuse over Residual Connections

    cs.LG 2024-11 conditional novelty 5.0 of 10

    A two-phase training algorithm alternating droppath steps with frozen-path steps gives modest accuracy improvements on small image datasets, with inconsistent ImageNet results.

  3. A Survey on Inference Optimization Techniques for Mixture of Experts Models

    cs.LG 2024-12 conditional novelty 3.0 of 10

    A structured survey of MoE inference optimization that categorizes existing techniques into model, system, and hardware levels and summarizes reported speedups and memory savings.

  4. Mixture of Experts (MoE): A Big Data Perspective

    cs.LG 2025-01 conditional novelty 2.0 of 10

    A survey of MoE methods for big data that catalogs architectures, use cases, and open challenges without adding new results.

Pith tools