Pith. sign in

REVIEW 1 cited by

The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse

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 2410.12766 v1 pith:TDPRPCQL submitted 2024-10-16 cs.LG

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

Model merging aims to efficiently combine the weights of multiple expert models, each trained on a specific task, into a single multi-task model, with strong performance across all tasks. When applied to all but the last layer of weights, existing methods -- such as Task Arithmetic, TIES-merging, and TALL mask merging -- work well to combine expert models obtained by fine-tuning a common foundation model, operating within a "local" neighborhood of the foundation model. This work explores the more challenging scenario of "non-local" merging, which we find arises when an expert model changes significantly during pretraining or where the expert models do not even share a common foundation model. We observe that standard merging techniques often fail to generalize effectively in this non-local setting, even when accounting for permutation symmetries using standard techniques. We identify that this failure is, in part, due to "variance collapse", a phenomenon identified also in the setting of linear mode connectivity by Jordan et al. (2023). To address this, we propose a multi-task technique to re-scale and shift the output activations of the merged model for each task, aligning its output statistics with those of the corresponding task-specific expert models. Our experiments demonstrate that this correction significantly improves the performance of various model merging approaches in non-local settings, providing a strong baseline for future research on this problem.

Discussion (0). Sign in 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. Continual Learning in Vision-Language Models via Aligned Model Merging

    cs.CV 2025-05 conditional novelty 5.0 of 10

    PAM merges a task-specific LoRA into a global LoRA and re-initializes sign-conflicting weights during training, reducing catastrophic forgetting in continual VLM learning.

Pith tools