Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Linear Explanations for Individual Neurons
Authors: Tuomas Oikarinen, Tsui-Wei Weng
ICML 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In Section 5, where we evaluate and compare our method and existing automated explanation methods. and 5. Experiment Results |
| Researcher Affiliation | Academia | 1CSE, UC San Diego, CA, USA 2HDSI, UC San Diego, CA, USA. Correspondence to: Tuomas Oikarinen <EMAIL>, Tsui-Wei Weng <EMAIL>. |
| Pseudocode | Yes | Algorithm 1 Greedy search. Python pseudo-code. |
| Open Source Code | Yes | Our code and results are available at https://github.com/TrustworthyML-Lab/Linear-Explanations. |
| Open Datasets | Yes | Res Net-50 (Image Net), Res Net-18 (Places365), VGG-16 (CIFAR-100), Vi T-B/16 (Image Net) |
| Dataset Splits | Yes | Throughout the paper we use a 70-10-20 split to divide our Dprobe into train, validation and test set splits to avoid overfitting our explanations. |
| Hardware Specification | Yes | Both of our explanation methods take around 4 seconds per explained neuron on a machine with a single Tesla V100 GPU. |
| Software Dependencies | No | No specific version numbers for key software components like programming languages or deep learning frameworks were provided. It mentions 'GLM-Saga package' and 'Sig LIP' but without versions. |
| Experiment Setup | Yes | In our experiments, (v, r, Ļµ) are set to be 10, 10, 0.02 respectively. and where RĪ·(wk) = (1 Ī·) 1 2||wk||2 2 + Ī·||wk||1 and Ī· is a hyperparameter, set to 0.99 in our experiments. |