Skip to content
View csinva's full-sized avatar
🎯
Focusing
🎯
Focusing

Organizations

@microsoft @conda-forge @BerkeleyML @Yu-Group @lumosvision @response4life @MicrosoftCopilot

Block or report csinva

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
csinva/README.md

Hi there πŸ‘‹ I'm Chandan, a Senior Researcher at Microsoft Research working on interpretable machine learning.
Homepage / Twitter / Google Scholar / LinkedIn 

🌳 Interpretable models / dataset explanations

Interpretable and accurate predictive modeling, sklearn-compatible (JOSS 2021). Contains FIGS (PNAS 2022) and HSTree (ICML 2022)

Interpretability for text. Contains Aug-imodels (Nature Communications 2023) , Tree-Prompt (EMNLP 2023) , iPrompt (ICLR workshop 2023) , SASC (NeurIPS workshop 2023) , and QA-Embs (NeurIPS 2024)

adaptive-wavelets Adaptive, interpretable wavelets (NeurIPS 2021)

πŸ€– General-purpose AI packages and cheatsheets

Notes and resources on AI

Utilities for trustworthy data-science (JOSS 2021)

🧠 Interpreting neural networks

deep-explanation-penalization Penalizing neural-network explanations (ICML 2020)

hierarchical-dnn-interpretations Hierarchical interpretations for neural network predictions (ICLR 2019)

transformation-importance Feature importance for transformations (ICLR Workshop 2020)

πŸ“Š Data-science problems

automated-brain-explanations Building natural-language explanations for the brain. Contains GCT (arxiv 2024)

clinical-rule-development Building and vetting clinical decision rules, including vetting an intraabdominal rule (PLOS Digital Health 2022), analyzing patient perspectives for approving rules (Kornblith et al. 2025, Nature scientific reports), or analyzing bias across CDIs (Obra et al. 2025). See also general PECARN data preprocessing (clinical-rule-vetting )

covid19-severity-prediction Extensive COVID-19 data + forecasting for counties and hospitals (HDSR 2021)

molecular-partner-prediction Predicting successful CME events using only clathrin markers

Various aspects of deep learning and machine learning

gan-vae-pretrained-pytorch Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch

gpt-paper-title-generator Generating paper titles with GPT-2

disentangled-attribution-curves Attribution curves for interpreting tree ensembles trees (arxiv 2019)

matching-with-gans Matching in GAN latent space for better bias benchmarking. (CVPR workshop 2021)

data-viz-utils Functions for easily making publication-quality figures with matplotlib

mdl-complexity Revisiting complexity and the bias-variance tradeoff (JMLR 2021)

Projects advised

pasta Post-hoc Attention Steering for LLMs (ICLR 2024), led by Qingru Zhang

meta-tree Learning a Decision Tree Algorithm with Transformers (TMLR 2024), led by Yufan Zhuang

sim-dino Simplifying DINO via coding rate regularization (arXiv 2025), led by Ziyang Wu

explanation-consistency-finetuning Consistent Natural-Language Explanations (COLING 2025), led by Yanda Chen

induction-gram Interpretable Language Modeling via Induction-head Ngram Models (arXiv 2024), led by Eunji Kim & Sriya Mantena

Open-source contributions

Major: autogluon , big-bench , nl-augmenter

Minor: conference-acceptance-rates , iterative-random-forest , interpretable-ml-book , awesome-interpretable-machine-learning , awesome-machine-learning-interpretability , awesome-llm-interpretability , executable-books , deep-fMRI-dataset

Mini-projects

hummingbird-tracking, imodels-experiments, cookiecutter-ml-research, nano-descriptions, news-title-bias, java-mini-games, imodels-data, news-balancer, arxiv-copier, dnn-experiments, max-activation-interpretation-pytorch, acronym-generator, hpa-interp, sensible-local-interpretations, global-sports-analysis, mouse-brain-decoding, ...

Pinned Loading

  1. imodels imodels Public

    Interpretable ML package πŸ” for concise, transparent, and accurate predictive modeling (sklearn-compatible).

    Jupyter Notebook 1.4k 124

  2. imodelsX imodelsX Public

    Interpret text data using LLMs (scikit-learn compatible).

    Python 163 26

  3. microsoft/automated-brain-explanations microsoft/automated-brain-explanations Public

    Generating and validating natural-language explanations for the brain.

    Jupyter Notebook 49 6

  4. clinical-rule-development clinical-rule-development Public

    Building and vetting clinical decision rules.

    Jupyter Notebook 8 2

  5. csinva.github.io csinva.github.io Public

    Slides, paper notes, class notes, blog posts, and research on ML πŸ“‰, statistics πŸ“Š, and AI πŸ€–.

    HTML 579 107

  6. hierarchical-dnn-interpretations hierarchical-dnn-interpretations Public

    Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

    Jupyter Notebook 128 23