Pith. sign in

REVIEW 2 cited by

Clusterability in Neural Networks

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 2103.03386 v1 pith:UXRCLC4E submitted 2021-03-04 cs.NE

classification cs.NE
keywords networksneuralclusterabilitynetworkclusterableconnectivityfindinternal
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The learned weights of a neural network have often been considered devoid of scrutable internal structure. In this paper, however, we look for structure in the form of clusterability: how well a network can be divided into groups of neurons with strong internal connectivity but weak external connectivity. We find that a trained neural network is typically more clusterable than randomly initialized networks, and often clusterable relative to random networks with the same distribution of weights. We also exhibit novel methods to promote clusterability in neural network training, and find that in multi-layer perceptrons they lead to more clusterable networks with little reduction in accuracy. Understanding and controlling the clusterability of neural networks will hopefully render their inner workings more interpretable to engineers by facilitating partitioning into meaningful clusters.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 5 citations worldwide. Full citation record

  1. Studying Cross-cluster Modularity in Neural Networks

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A clusterability regularizer creates strongly separated clusters in neural networks, shrinking effective circuit size by up to 90% on CIFAR-10, but it does not create task-specialized modules.

  2. Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii

    cs.LG 2025-05 conditional novelty 5.0 of 10

    The paper introduces an Explanatory Virtues Framework and argues, via a qualitative rubric, that Compact Proofs are the most promising method for mechanistic interpretability.

Pith tools