RobertCsordas / modules
The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.
☆46Updated last year
Alternatives and similar repositories for modules:
Users that are interested in modules are comparing it to the libraries listed below
- ☆30Updated 9 months ago
- ☆45Updated 2 years ago
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆31Updated 4 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- Official code for "In Search of Robust Measures of Generalization" (NeurIPS 2020)☆28Updated 4 years ago
- ☆34Updated 3 years ago
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆75Updated last year
- Compositional Explanations of Neurons, NeurIPS 2020 https://arxiv.org/abs/2006.14032☆25Updated 4 years ago
- ☆34Updated 4 years ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 3 years ago
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆105Updated last year
- The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)☆39Updated last year
- Group-conditional DRO to alleviate spurious correlations☆15Updated 3 years ago
- ☆18Updated last year
- ☆60Updated 3 years ago
- ☆62Updated 3 years ago
- ☆82Updated 8 months ago
- ☆24Updated 4 years ago
- ☆19Updated 3 years ago
- Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?☆40Updated 2 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year
- ☆54Updated 4 years ago
- ☆65Updated 9 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- ☆38Updated 3 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆71Updated 11 months ago
- Toy datasets to evaluate algorithms for domain generalization and invariance learning.☆42Updated 3 years ago
- Energy-Based Models for Continual Learning Official Repository (PyTorch)☆41Updated 2 years ago
- Codes and scripts for "Explainable Semantic Space by Grounding Languageto Vision with Cross-Modal Contrastive Learning"☆21Updated 3 years ago
- "Predict, then Interpolate: A Simple Algorithm to Learn Stable Classifiers" ICML 2021☆18Updated 3 years ago