# ModelDiff: A Framework for Comparing Learning Algorithms

arXiv: https://arxiv.org/abs/2211.12491 · HTML: https://mlsanity.com/paper/2211.12491/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 80 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 30 of 56)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [What is being transferred in transfer learning?](https://mlsanity.com/paper/2008.11687/) (2020)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [Train longer, generalize better: closing the generalization gap in large batch training of neural networks](https://mlsanity.com/paper/1705.08741/) (2017)
- [Real Time Image Saliency for Black Box Classifiers](https://mlsanity.com/paper/1705.07857/) (2017)
- [Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth](https://mlsanity.com/paper/2010.15327/) (2020)
- [Convergent Learning: Do different neural networks learn the same representations?](https://mlsanity.com/paper/1511.07543/) (2015)
- [Revisiting Model Stitching to Compare Neural Representations](https://mlsanity.com/paper/2106.07682/) (2021)
- [Datamodels: Predicting Predictions from Training Data](https://mlsanity.com/paper/2202.00622/) (2022)
- [Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks](https://mlsanity.com/paper/1907.04595/) (2019)
- [Domino: Discovering Systematic Errors with Cross-Modal Embeddings](https://mlsanity.com/paper/2203.14960/) (2022)
- [BREEDS: Benchmarks for Subpopulation Shift](https://mlsanity.com/paper/2008.04859/) (2020)

## Built on by (most cited first, 30 of 30)

- [TRAK: Attributing Model Behavior at Scale](https://mlsanity.com/paper/2303.14186/) (2023)
- [Similarity of Neural Network Models: A Survey of Functional and Representational Measures](https://mlsanity.com/paper/2305.06329/) (2023)
- [Describing Differences in Image Sets with Natural Language](https://mlsanity.com/paper/2312.02974/) (2023)
- [The Journey, Not the Destination: How Data Guides Diffusion Models](https://mlsanity.com/paper/2312.06205/) (2023)
- [Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning](https://mlsanity.com/paper/2504.02922/) (2025)
- [FACTS: First Amplify Correlations and Then Slice to Discover Bias](https://mlsanity.com/paper/2309.17430/) (2023)
- [CUPID: Curating Data your Robot Loves with Influence Functions](https://mlsanity.com/paper/2506.19121/) (2025)
- [Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models](https://mlsanity.com/paper/2410.18639/) (2024)
- [MAGIC: Near-Optimal Data Attribution for Deep Learning](https://mlsanity.com/paper/2504.16430/) (2025)
- [Understanding the Detrimental Class-level Effects of Data Augmentation](https://mlsanity.com/paper/2401.01764/) (2023)
- [DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations](https://mlsanity.com/paper/2311.17833/) (2023)
- [Simple Mechanistic Explanations for Out-Of-Context Reasoning](https://mlsanity.com/paper/2507.08218/) (2025)
- [AI Supply Chains: An Emerging Ecosystem of AI Actors, Products, and Services](https://mlsanity.com/paper/2504.20185/) (2025)
- [Towards Measuring Representational Similarity of Large Language Models](https://mlsanity.com/paper/2312.02730/) (2023)
- [A Simple and Efficient Baseline for Data Attribution on Images](https://mlsanity.com/paper/2311.03386/) (2023)
- [Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection](https://mlsanity.com/paper/2406.16846/) (2024)
- [Representational Similarity via Interpretable Visual Concepts](https://mlsanity.com/paper/2503.15699/) (2025)
- [A Lightweight Measure of Classification Difficulty from Application Dataset Characteristics](https://mlsanity.com/paper/2404.05981/) (2024)
- [MD tree: a model-diagnostic tree grown on loss landscape](https://mlsanity.com/paper/2406.16988/) (2024)
- [Scaling laws for activation steering with Llama 2 models and refusal mechanisms](https://mlsanity.com/paper/2507.11771/) (2025)
- [Bergson: An Open Source Library for Data Attribution](https://mlsanity.com/paper/2606.11660/) (2026)
- [Investigating the Effects of Fairness Interventions Using Pointwise Representational Similarity](https://mlsanity.com/paper/2305.19294/) (2023)
- [Small-to-Large Generalization: Data Influences Models Consistently Across Scale](https://mlsanity.com/paper/2505.16260/) (2025)
- [Origin Tracer: A Method for Detecting LoRA Fine-Tuning Origins in LLMs](https://mlsanity.com/paper/2505.19466/) (2025)
- [Understanding the Benefits of Image Augmentations](https://mlsanity.com/paper/2306.06254/) (2023)
- [Perturbed examples reveal invariances shared by language models](https://mlsanity.com/paper/2311.04166/) (2023)
- [ImageSet2Text: Describing Sets of Images through Text](https://mlsanity.com/paper/2503.19361/) (2025)
- [RedunCut: Measurement-Driven Sampling and Accuracy Performance Modeling for Low-Cost Live Video Analytics](https://mlsanity.com/paper/2512.24386/) (2025)
- [Efficient Neural Network Model Selection for Few-Class Application Datasets](https://mlsanity.com/paper/2606.19712/) (2026)
- [Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States](https://mlsanity.com/paper/2609.10060/) (2026)

## Abstract (arXiv)

We study the problem of (learning) algorithm comparison, where the goal is to find differences between models trained with two different learning algorithms. We begin by formalizing this goal as one of finding distinguishing feature transformations, i.e., input transformations that change the predictions of models trained with one learning algorithm but not the other. We then present ModelDiff, a method that leverages the datamodels framework (Ilyas et al., 2022) to compare learning algorithms based on how they use their training data. We demonstrate ModelDiff through three case studies, comparing models trained with/without data augmentation, with/without pre-training, and with different SGD hyperparameters. Our code is available at https://github.com/MadryLab/modeldiff .