LGCLSep 1, 2023

NeuroSurgeon: A Toolkit for Subnetwork Analysis

arXiv:2309.00244v19 citationsHas Code
Originality Synthesis-oriented
AI Analysis

This provides a tool for researchers in explainable AI to analyze functional circuits in neural networks, but it is incremental as it builds on existing decomposition methods.

The authors tackled the problem of understanding neural networks by developing NeuroSurgeon, a toolkit for discovering and manipulating subnetworks in Huggingface Transformers models, resulting in a freely available Python library.

Despite recent advances in the field of explainability, much remains unknown about the algorithms that neural networks learn to represent. Recent work has attempted to understand trained models by decomposing them into functional circuits (Csordás et al., 2020; Lepori et al., 2023). To advance this research, we developed NeuroSurgeon, a python library that can be used to discover and manipulate subnetworks within models in the Huggingface Transformers library (Wolf et al., 2019). NeuroSurgeon is freely available at https://github.com/mlepori1/NeuroSurgeon.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes