Pith. sign in

REVIEW 1 cited by

SimSMoE: Solving Representational Collapse via Similarity Measure

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 2406.15883 v1 pith:4HJ552HM submitted 2024-06-22 cs.CL cs.AI

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

Sparse mixture of experts (SMoE) have emerged as an effective approach for scaling large language models while keeping a constant computational cost. Regardless of several notable successes of SMoE, effective training such architecture remains elusive due to the representation collapse problem, which in turn harms model performance and causes parameter redundancy. In this work, we present Similarity-based Sparse Mixture of Experts (SimSMoE), a novel similarity of neural network algorithm, that guarantees a solution to address the representation collapse issue between experts given a fixed FLOPs budget. We conduct extensive empirical evaluations on three large language models for both Pre-training and Fine-tuning tasks to illustrate the efficacy, robustness, and scalability of our method. The results demonstrate that SimSMoE significantly enhances existing routing policy and outperforms other SMoE training methods in performance for the tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. On the Role of Discrete Representation in Sparse Mixture of Experts

    cs.LG 2024-11 reject novelty 6.0 of 10

    VQMoE is a routing-free SMoE variant using vector-quantized discrete codes for expert selection; its empirical gains are small and its theoretical proofs are circular or unsupported.

Pith tools