Skip to yearly menu bar Skip to main content


Workshop

The Second Workshop on Spurious Correlations, Invariance and Stability

Yoav Wald ⋅ Claudia Shi ⋅ Aahlad Puli ⋅ Amir Feder ⋅ Limor Gultchin ⋅ Mark Goldstein ⋅ Maggie Makar ⋅ Victor Veitch ⋅ Uri Shalit
Project Page

Abstract

Video

Chat is not available.

Schedule

Timezone: Asia/Seoul
3:50 AM
Opening Remarks
4:45 AM
Paper Spotlights
Andrew Ilyas ⋅ Alizée Pace ⋅ Ji Won Park ⋅ Adam Breitholtz ⋅ Nari Johnson
5:15 AM
Break
6:15 AM
Using Causality to Improve Safety Throughout the AI Lifecycle
Suchi Saria ⋅ Adarsh Subbaswamy
7:00 AM
Lunch Break
10:30 AM
SCIS 2023 Panel, The Future of Generalization: Scale, Safety and Beyond
Maggie Makar ⋅ Samuel Bowman ⋅ Zachary Lipton ⋅ Adam Gleave
Fairness-Preserving Regularizer: Balancing Core and Spurious Features
Jiawei Feng ⋅ Ancong Wu ⋅ YuHan Yao ⋅ Wei-Shi Zheng
Identifying and Disentangling Spurious Features in Pretrained Image Representations
Rafayel Darbinyan ⋅ Hrayr Harutyunyan ⋅ Aram Markosyan ⋅ Hrant Khachatrian
Temporal Consistency based Test Time Adaptation: Towards Fair and Personalized AI
Mohammadmahdi Honarmand ⋅ Onur Cezmi Mutlu ⋅ Saimourya Surabhi ⋅ Dennis Wall
Regularizing Model Gradients with Concepts to Improve Robustness to Spurious Correlations
Yiwei Yang ⋅ Anthony Liu ⋅ Robert Wolfe ⋅ Aylin Caliskan ⋅ Bill Howe
Spuriosity Didn’t Kill the Classifier: Using Invariant Predictions to Harness Spurious Features
Cian Eastwood ⋅ Shashank Singh ⋅ Andrei Nicolicioiu ⋅ Marin Vlastelica ⋅ Julius von Kügelgen ⋅ Bernhard Schölkopf
Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift
Saurabh Garg ⋅ Amrith Setlur ⋅ Zachary Lipton ⋅ Sivaraman Balakrishnan ⋅ Virginia Smith ⋅ Aditi Raghunathan
Spurious Correlations and Where to Find Them
Gautam Sreekumar ⋅ Vishnu Boddeti
Why is SAM Robust to Label Noise?
Christina Baek ⋅ Zico Kolter ⋅ Aditi Raghunathan
Confident feature ranking
Bitya Neuhof ⋅ Yuval Benjamini
Calibrated Propensities for Causal Effect Estimation
Shachi Deshpande ⋅ Volodymyr Kuleshov
Understanding the Detrimental Class-level Effects of Data Augmentation
Polina Kirichenko ⋅ Mark Ibrahim ⋅ Randall Balestriero ⋅ Diane Bouchacourt ⋅ Ramakrishna Vedantam ⋅ Hamed Firooz ⋅ Andrew Wilson
Feature Selection in the Presence of Monotone Batch Effects
Peng Dai ⋅ Sina Baharlouei ⋅ Meisam Razaviyayn ⋅ Sze-Chuan Suen
Exploring new ways: Enforcing representational dissimilarity to learn new features and reduce error consistency
Tassilo Wald ⋅ Constantin Ulrich ⋅ Fabian Isensee ⋅ David Zimmerer ⋅ Gregor Koehler ⋅ Michael Baumgartner ⋅ Klaus Maier-Hein
Where Does My Model Underperform?: A Human Evaluation of Slice Discovery Algorithms
Nari Johnson ⋅ Ángel Alexander Cabrera ⋅ Gregory Plumb ⋅ Ameet Talwalkar
Complementing a Policy with a Different Observation Space
Gokul Swamy ⋅ Sanjiban Choudhury ⋅ J. Bagnell ⋅ Steven Wu
Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks
Yuzhen Mao ⋅ Zhun Deng ⋅ Huaxiu Yao ⋅ Ting Ye ⋅ Kenji Kawaguchi ⋅ James Zou
Separating multimodal modeling from multidimensional modeling for multimodal learning
Divyam Madaan ⋅ Taro Makino ⋅ Sumit Chopra ⋅ Kyunghyun Cho
Do as your neighbors: Invariant learning through non-parametric neighbourhood matching
Andrei Nicolicioiu ⋅ Jerry Huang ⋅ Dhanya Sridhar ⋅ Aaron Courville
Leveraging sparse and shared feature activations for disentangled representation learning
Marco Fumero ⋅ Florian Wenzel ⋅ Luca Zancato ⋅ Alessandro Achille ⋅ Emanuele Rodola ⋅ Stefano Soatto ⋅ Bernhard Schölkopf ⋅ Francesco Locatello
Which Features are Learned by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression
Yihao Xue ⋅ Siddharth Joshi ⋅ Eric Gan ⋅ Pin-Yu Chen ⋅ Baharan Mirzasoleiman
Cross-Risk Minimization: Inferring Groups Information for Improved Generalization
Mohammad Pezeshki ⋅ Diane Bouchacourt ⋅ Mark Ibrahim ⋅ Nicolas Ballas ⋅ Pascal Vincent ⋅ David Lopez-Paz
Robustness through Loss Consistency Regularization
Tianjian Huang ⋅ Shaunak Halbe ⋅ Chinnadhurai Sankar ⋅ Pooyan Amini ⋅ Satwik Kottur ⋅ Alborz Geramifard ⋅ Meisam Razaviyayn ⋅ Ahmad Beirami
Learning Diverse Features in Vision Transformers for Improved Generalization
Armand Nicolicioiu ⋅ Andrei Nicolicioiu ⋅ Bogdan Alexe ⋅ Damien Teney
Sharpness-Aware Minimization Enhances Feature Diversity
Jacob Mitchell Springer ⋅ Vaishnavh Nagarajan ⋅ Aditi Raghunathan
ERM++: An Improved Baseline for Domain Generalization
Piotr Teterwak ⋅ Kuniaki Saito ⋅ Theodoros Tsiligkaridis ⋅ Kate Saenko ⋅ Bryan Plummer
Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge
Abhin Shah ⋅ Karthikeyan Shanmugam ⋅ Murat Kocaoglu
Group Fairness with Uncertainty in Sensitive Attributes
Abhin Shah ⋅ Maohao Shen ⋅ Jongha Ryu ⋅ Subhro Das ⋅ Prasanna Sattigeri ⋅ Yuheng Bu ⋅ Gregory Wornell
Data Models for Dataset Drift Controls in Machine Learning With Optical Images
Luis Oala ⋅ Marco Aversa ⋅ Gabriel Nobis ⋅ Kurt Willis ⋅ Yoan Neuenschwander ⋅ Michèle Buck ⋅ Christian Matek ⋅ Jerome Extermann ⋅ Enrico Pomarico ⋅ Wojciech Samek ⋅ Roderick Murray-Smith ⋅ Christoph Clausen ⋅ Bruno Sanguinetti
Arbitrary Decisions are a Hidden Cost of Differentially Private Training
Bogdan Kulynych ⋅ Hsiang Hsu ⋅ Carmela Troncoso ⋅ Flavio Calmon
Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift
Benjamin Eyre ⋅ Elliot Creager ⋅ David Madras ⋅ Vardan Papyan ⋅ Richard Zemel
Prediction without Preclusion: Recourse Verification with Reachable Sets
Avni Kothari ⋅ Bogdan Kulynych ⋅ Lily Weng ⋅ Berk Ustun
Removing Multiple Biases through the Lens of Multi-task Learning
Nayeong Kim ⋅ Juwon Kang ⋅ Sungsoo Ahn ⋅ Jungseul Ok ⋅ Suha Kwak
Learning Independent Causal Mechanisms
Sarah Mameche ⋅ David Kaltenpoth ⋅ Jilles Vreeken
Towards Fair Knowledge Distillation using Student Feedback
Abhinav Java ⋅ Surgan Jandial ⋅ Chirag Agarwal
Provable domain adaptation using privileged information
Adam Breitholtz ⋅ Anton Matsson ⋅ Fredrik Johansson
A Cosine Similarity-based Method for Out-of-Distribution Detection
Ngoc Hieu Nguyen ⋅ Nguyen Hung-Quang ⋅ The-Anh Ta ⋅ Thanh Nguyen-Tang ⋅ Khoa Doan ⋅ Hoang Thanh-Tung
Reviving Shift Equivariance in Vision Transformers
Peijian Ding ⋅ Davit Soselia ⋅ Thomas Armstrong ⋅ Jiahao Su ⋅ Furong Huang
Identifiability Guarantees for Causal Disentanglement from Soft Interventions
Jiaqi Zhang ⋅ Chandler Squires ⋅ Kristjan Greenewald ⋅ Akash Srivastava ⋅ Karthikeyan Shanmugam ⋅ Caroline Uhler
Towards A Scalable Solution for Compositional Multi-Group Fair Classification
James Atwood ⋅ Tina Tian ⋅ Ben Packer ⋅ Meghana Deodhar ⋅ Jilin Chen ⋅ Alex Beutel ⋅ Flavien Prost ⋅ Ahmad Beirami
Towards Modular Learning of Deep Causal Generative Models
Md Musfiqur Rahman ⋅ Murat Kocaoglu
Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding
Alizée Pace ⋅ Hugo Yèche ⋅ Bernhard Schölkopf ⋅ Gunnar Ratsch ⋅ Guy Tennenholtz
C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder
Xiaoyu Liu ⋅ Jiaxin Yuan ⋅ Bang An ⋅ Yuancheng Xu ⋅ Yifan Yang ⋅ Furong Huang
Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning
Yu Yang ⋅ Besmira Nushi ⋅ Hamid Palangi ⋅ Baharan Mirzasoleiman
Adversarial Data Augmentations for Out-of-Distribution Generalization
Simon Zhang ⋅ Ryan DeMilt ⋅ Kun Jin ⋅ Cathy Honghui Xia
Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models
Tianyu Chen ⋅ Kevin Bello ⋅ Bryon Aragam ⋅ Pradeep Ravikumar
Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline Reinforcement Learning
PENG CHENG ⋅ Xianyuan Zhan ⋅ Zhihao Wu ⋅ Wenjia Zhang ⋅ Youfang Lin ⋅ Shou cheng Song ⋅ Han Wang
Learning Linear Causal Representations from Interventions under General Nonlinear Mixing
Simon Buchholz ⋅ Goutham Rajendran ⋅ Elan Rosenfeld ⋅ Bryon Aragam ⋅ Bernhard Schölkopf ⋅ Pradeep Ravikumar
Identifiability of Discretized Latent Coordinate Systems via Density Landmarks Detection
Vitória Barin-Pacela ⋅ Kartik Ahuja ⋅ Simon Lacoste-Julien ⋅ Pascal Vincent
Neuro-Causal Factor Analysis
Alex Markham ⋅ Mingyu Liu ⋅ Bryon Aragam ⋅ Liam Solus
Deep Neural Networks Extrapolate Cautiously (Most of the Time)
Katie Kang ⋅ Amrith Setlur ⋅ Claire Tomlin ⋅ Sergey Levine
Approximate Causal Effect Identification under Weak Confounding
Ziwei Jiang ⋅ Lai Wei ⋅ Murat Kocaoglu
Robust Learning with Progressive Data Expansion Against Spurious Correlation
Yihe Deng ⋅ Yu Yang ⋅ Baharan Mirzasoleiman ⋅ Quanquan Gu
Towards Understanding Feature Learning in Out-of-Distribution Generalization
Yongqiang Chen ⋅ Wei Huang ⋅ Kaiwen Zhou ⋅ Yatao Bian ⋅ Bo Han ⋅ James Cheng
Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection
Mohammad Azizmalayeri ⋅ reza abbasi ⋅ Amir Hosein Haji Mohammad rezaie ⋅ Reihaneh Zohrabi ⋅ Mahdi Amiri ⋅ Mohammad Manzuri ⋅ Mohammad H Rohban
Leveraging Task Structures for Improved Identifiability in Neural Network Representations
Wenlin Chen ⋅ Julien Horwood ⋅ Juyeon Heo ⋅ Jose Miguel Hernandez-Lobato
Learning Counterfactually Invariant Predictors
Francesco Quinzan ⋅ Cecilia Casolo ⋅ Krikamol Muandet ⋅ Yucen Luo ⋅ Niki Kilbertus
Concept Algebra for Score-based Conditional Model
Zihao Wang ⋅ Lin Gui ⋅ Jeffrey Negrea ⋅ Victor Veitch
Tackling Shortcut Learning in Deep Neural Networks: An Iterative Approach with Interpretable Models
Shantanu Ghosh ⋅ Ke Yu ⋅ Forough Arabshahi ⋅ Kayhan Batmanghelich
Invariant Causal Set Covering Machines
Thibaud Godon ⋅ Baptiste Bauvin ⋅ Pascal Germain ⋅ Jacques Corbeil ⋅ Alexandre Drouin
Replicable Reinforcement Learning
ERIC EATON ⋅ Marcel Hussing ⋅ Michael Kearns ⋅ Jessica Sorrell
Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation
Wenhao Ding ⋅ Laixi Shi ⋅ Yuejie Chi ⋅ Ding Zhao
Shortcut Detection with Variational Autoencoders
Nicolas Müller ⋅ Simon Roschmann ⋅ Shahbaz Khan ⋅ Philip Sperl ⋅ Konstantin Böttinger
Results on Counterfactual Invariance
Jake Fawkes ⋅ Robin Evans
The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-language Models
Chenwei Wu ⋅ Li Li ⋅ Stefano Ermon ⋅ Patrick Haffner ⋅ Rong Ge ⋅ Zaiwei Zhang
Bridging the Domain Gap by Clustering-based Image-Text Graph Matching
Nokyung Park ⋅ Daewon Chae ⋅ Jeong Yong Shim ⋅ Sangpil Kim ⋅ Eun-Sol Kim ⋅ Jinkyu Kim
ModelDiff: A Framework for Comparing Learning Algorithms
Harshay Shah ⋅ Sung Min (Sam) Park ⋅ Andrew Ilyas ⋅ Aleksander Madry
Improve Identity-Robustness for Face Models
Qi Qi ⋅ Shervin Ardeshir
Impact of Noise on Calibration and Generalisation of Neural Networks
Martin Ferianc ⋅ Ondrej Bohdal ⋅ Timothy Hospedales ⋅ Miguel Rodrigues
Bias-to-Text: Debiasing Unknown Visual Biases by Language Interpretation
Younghyun Kim ⋅ Sangwoo Mo ⋅ Minkyu Kim ⋅ Kyungmin Lee ⋅ Jaeho Lee ⋅ Jinwoo Shin
Studying Generalization on Memory-Based Methods in Continual Learning
Felipe del Rio ⋅ Julio Hurtado ⋅ Cristian Calderon ⋅ Alvaro Soto ⋅ Vincenzo Lomonaco
Causal Dynamics Learning with Quantized Local Independence Discovery
Inwoo Hwang ⋅ Yunhyeok Kwak ⋅ Suhyung Choi ⋅ Byoung-Tak Zhang ⋅ Sanghack Lee
Shortcut Learning Through the Lens of Training Dynamics
Nihal Murali ⋅ Aahlad Puli ⋅ Ke Yu ⋅ Rajesh Ranganath ⋅ Kayhan Batmanghelich
Optimization or Architecture: What Matters in Non-Linear Filtering?
Ido Greenberg ⋅ Netanel Yannay ⋅ Shie Mannor
Causal-structure Driven Augmentations for Text OOD Generalization
Amir Feder ⋅ Yoav Wald ⋅ Claudia Shi ⋅ Suchi Saria ⋅ David Blei
Weighted Risk Invariance for Density-Aware Domain Generalization
Gina Wong ⋅ Joshua Gleason ⋅ Rama Chellappa ⋅ Yoav Wald ⋅ Anqi Liu