Pith. sign in

REVIEW 1 cited by

Quantifying Local Specialization in Deep 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 2110.08058 v2 pith:N3F5SAXW submitted 2021-10-13 cs.LG cs.AIcs.NE

Quantifying Local Specialization in Deep Neural Networks

classification cs.LG cs.AIcs.NE
keywords neuronsnetworkneuralproxiesspecializedabstractlyclustersdeep
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

A neural network is locally specialized to the extent that parts of its computational graph (i.e. structure) can be abstractly represented as performing some comprehensible sub-task relevant to the overall task (i.e. functionality). Are modern deep neural networks locally specialized? How can this be quantified? In this paper, we consider the problem of taking a neural network whose neurons are partitioned into clusters, and quantifying how functionally specialized the clusters are. We propose two proxies for this: importance, which reflects how crucial sets of neurons are to network performance; and coherence, which reflects how consistently their neurons associate with features of the inputs. To measure these proxies, we develop a set of statistical methods based on techniques conventionally used to interpret individual neurons. We apply the proxies to partitionings generated by spectrally clustering a graph representation of the network's neurons with edges determined either by network weights or correlations of activations. We show that these partitionings, even ones based only on weights (i.e. strictly from non-runtime analysis), reveal groups of neurons that are important and coherent. These results suggest that graph-based partitioning can reveal local specialization and that statistical methods can be used to automatedly screen for sets of neurons that can be understood abstractly.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

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

  1. Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?

    cs.AI 2026-07 reject novelty 3.0

    Weight magnitude is a weak and nonlinear proxy for per-weight importance in CNNs, but the paper's quantitative claims are undermined by a mislabeled metric and an unconventional definition of 'neuron'.