Skip to yearly menu bar Skip to main content


Workshop

Trustworthy and Socially Responsible Machine Learning

Huan Zhang ⋅ Linyi Li ⋅ Chaowei Xiao ⋅ J. Zico Kolter ⋅ Anima Anandkumar ⋅ Bo Li
Project Page [ Contact: tsrml2022@googlegroups.com ]

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
6:45 AM
Introduction and Opening Remarks
Huan Zhang ⋅ Linyi Li
7:00 AM
Invited Talk: Aleksander Mądry
Aleksander Madry
7:30 AM
Contributed Talk: Revisiting Robustness in Graph Machine Learning
Lukas Gosch ⋅ Daniel Sturm ⋅ Simon Geisler ⋅ Stephan Günnemann
8:00 AM
Invited Talk: Milind Tambe
Milind Tambe
8:30 AM
Coffee Break I
9:30 AM
Invited Talk: Nika Haghtalab
Nika Haghtalab
10:00 AM
Invited Talk: Kamalika Chaudhuri
Kamalika Chaudhuri
10:30 AM
Invited Talk: Been Kim
Been Kim
11:00 AM
Lunch Break
12:00 PM
Invited Talk: Yi Ma
Yi Ma
12:30 PM
Invited Talk: Dorsa Sadigh
Dorsa Sadigh
1:00 PM
Invited Talk: Marco Pavone
Marco Pavone
1:30 PM
Contributed Talk: DensePure: Understanding Diffusion Models towards Adversarial Robustness
Zhongzhu Chen ⋅ Kun Jin ⋅ Jiongxiao Wang ⋅ Weili Nie ⋅ Mingyan Liu ⋅ Anima Anandkumar ⋅ Bo Li ⋅ Dawn Song
2:45 PM
Contributed Talk: Differentially Private Bias-Term only Fine-tuning of Foundation Models
Zhiqi Bu ⋅ Yu-Xiang Wang ⋅ Sheng Zha ⋅ George Karypis
2:45 PM
Contributed Talk: TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations
Dylan Slack ⋅ Satyapriya Krishna ⋅ Himabindu Lakkaraju ⋅ Sameer Singh
3:00 PM
Contributed Talk: zPROBE: Zero Peek Robustness Checks for Federated Learning
Zahra Ghodsi ⋅ Mojan Javaheripi ⋅ Nojan Sheybani ⋅ Xinqiao Zhang ⋅ Ke Huang ⋅ Farinaz Koushanfar
3:15 PM
Panel Discussion
Kamalika Chaudhuri ⋅ Been Kim ⋅ Dorsa Sadigh ⋅ Huan Zhang ⋅ Linyi Li
4:00 PM
Closing Remarks
Huan Zhang ⋅ Linyi Li
Improving Fairness in Image Classification via Sketching
Ruichen Yao ⋅ cui ziteng ⋅ Xiaoxiao Li ⋅ Lin Gu
Case Study: Applying Decision Focused Learning in the Real World
Shresth Verma ⋅ Aditya Mate ⋅ Kai Wang ⋅ Aparna Taneja ⋅ Milind Tambe
Generating Intuitive Fairness Specifications for Natural Language Processing
Florian E. Dorner ⋅ Momchil Peychev ⋅ Nikola Konstantinov ⋅ Naman Goel ⋅ Elliott Ash ⋅ Martin Vechev
Learning from uncertain concepts via test time interventions
Ivaxi Sheth ⋅ Aamer Abdul Rahman ⋅ Laya Rafiee Sevyeri ⋅ Mohammad Havaei ⋅ Samira Ebrahimi Kahou
Towards Reasoning-Aware Explainable VQA
Rakesh Vaideeswaran ⋅ Feng Gao ⋅ ABHINAV MATHUR ⋅ Govindarajan Thattai
Beyond Protected Attributes: Disciplined Detection of Systematic Deviations in Data
Adebayo Oshingbesan ⋅ Winslow Omondi ⋅ Girmaw Abebe Tadesse ⋅ Celia Cintas ⋅ Skyler D. Speakman
A Stochastic Optimization Framework for Fair Risk Minimization
Andrew Lowy ⋅ Sina Baharlouei ⋅ Rakesh Pavan ⋅ Meisam Razaviyayn ⋅ Ahmad Beirami
On the Trade-Off between Actionable Explanations and the Right to be Forgotten
Martin Pawelczyk ⋅ Tobias Leemann ⋅ Asia Biega ⋅ Gjergji Kasneci
But Are You Sure? Quantifying Uncertainty in Model Explanations
Charles Marx ⋅ Youngsuk Park ⋅ Hilaf Hasson ⋅ Yuyang (Bernie) Wang ⋅ Stefano Ermon ⋅ Chaitanya Baru
Fairness-aware Missing Data Imputation
Yiliang Zhang ⋅ Qi Long
Socially Responsible Reasoning with Large Language Models and The Impact of Proper Nouns
Sumit Jha ⋅ Rickard Ewetz ⋅ Alvaro Velasquez ⋅ Susmit Jha
When Personalization Harms: Reconsidering the Use of Group Attributes of Prediction
Vinith Suriyakumar ⋅ Marzyeh Ghassemi ⋅ Berk Ustun
Denoised Smoothing with Sample Rejection for Robustifying Pretrained Classifiers
Fatemeh Sheikholeslami ⋅ Wan-Yi Lin ⋅ Jan Hendrik Metzen ⋅ Huan Zhang ⋅ J. Zico Kolter
On the Robustness of deep learning-based MRI Reconstruction to image transformations
jinghan jia ⋅ Mingyi Hong ⋅ Yimeng Zhang ⋅ Mehmet Akcakaya ⋅ Sijia Liu
Real world relevance of generative counterfactual explanations
Swami Sankaranarayanan ⋅ Thomas Hartvigsen ⋅ Lauren Oakden-Rayner ⋅ Marzyeh Ghassemi ⋅ Phillip Isola
Quantifying Social Biases Using Templates is Unreliable
Preethi Seshadri ⋅ Pouya Pezeshkpour ⋅ Sameer Singh
DensePure: Understanding Diffusion Models towards Adversarial Robustness
Zhongzhu Chen ⋅ Kun Jin ⋅ Jiongxiao Wang ⋅ Weili Nie ⋅ Mingyan Liu ⋅ Anima Anandkumar ⋅ Bo Li ⋅ Dawn Song
A Fair Loss Function for Network Pruning
Robbie Meyer ⋅ Alexander Wong
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of the Final Model
Nathalie Baracaldo ⋅ Kevin Eykholt ⋅ Farhan Ahmed ⋅ Yi Zhou ⋅ Shriti Priya ⋅ Taesung Lee ⋅ Swanand Kadhe ⋅ Yusong Tan ⋅ Sridevi Polavaram ⋅ Sterling Suggs
Private Data Leakage via Exploiting Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems
Hanieh Hashemi ⋅ Wenjie Xiong ⋅ Liu Ke ⋅ Kiwan Maeng ⋅ Murali Annavaram ⋅ G. Edward Suh ⋅ Hsien-Hsin Lee
Forgetting Data from Pre-trained GANs
Zhifeng Kong ⋅ Kamalika Chaudhuri
Training Differentially Private Graph Neural Networks with Random Walk Sampling
Morgane Ayle ⋅ Jan Schuchardt ⋅ Lukas Gosch ⋅ Daniel Zügner ⋅ Stephan Günnemann
Physically-Constrained Adversarial Attacks on Brain-Machine Interfaces
Xiaying Wang ⋅ Rodolfo Octavio Siller Quintanilla ⋅ Michael Hersche ⋅ Luca Benini ⋅ Gagandeep Singh
Striving for data-model efficiency: Identifying data externalities on group performance
Esther Rolf ⋅ Ben Packer ⋅ Alex Beutel ⋅ Fernando Diaz
A Closer Look at the Intervention Procedure of Concept Bottleneck Models
Sungbin Shin ⋅ Yohan Jo ⋅ Sungsoo Ahn ⋅ Namhoon Lee
Revisiting Robustness in Graph Machine Learning
Lukas Gosch ⋅ Daniel Sturm ⋅ Simon Geisler ⋅ Stephan Günnemann
Cooperation or Competition: Avoiding Player Domination for Multi-target Robustness by Adaptive Budgets
Yimu Wang ⋅ Dinghuai Zhang ⋅ Yihan Wu ⋅ Heng Huang ⋅ Hongyang Zhang
GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hint
Paiheng Xu ⋅ Yuhang Zhou ⋅ Bang An ⋅ Wei Ai ⋅ Furong Huang
Uncertainty-aware predictive modeling for fair data-driven decisions
Patrick Kaiser ⋅ Christoph Kern ⋅ David Rügamer
Information-Theoretic Evaluation of Free-Text Rationales with Conditional $\mathcal{V}$-Information
Hanjie Chen ⋅ Faeze Brahman ⋅ Xiang Ren ⋅ Yangfeng Ji ⋅ Yejin Choi ⋅ Swabha Swayamdipta
Interactive Rationale Extraction for Text Classification
Jiayi Dai ⋅ Mi-Young Kim ⋅ Randolph Goebel
Just Avoid Robust Inaccuracy: Boosting Robustness Without Sacrificing Accuracy
Yannick Merkli ⋅ Pavol Bielik ⋅ Petar Tsankov ⋅ Martin Vechev
Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model
Jacob Eisenstein ⋅ Daniel Andor ⋅ Bernd Bohnet ⋅ Michael Collins ⋅ David Mimno
Accelerating Open Science for AI in Heliophysics
Dolores Garcia ⋅ Paul Wright ⋅ Mark Cheung ⋅ Meng Jin ⋅ James Parr
A Theory of Learning with Competing Objectives and User Feedback
Pranjal Awasthi ⋅ Corinna Cortes ⋅ Yishay Mansour ⋅ Mehryar Mohri
zPROBE: Zero Peek Robustness Checks for Federated Learning
Zahra Ghodsi ⋅ Mojan Javaheripi ⋅ Nojan Sheybani ⋅ Xinqiao Zhang ⋅ Ke Huang ⋅ Farinaz Koushanfar
PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales
Peifeng Wang ⋅ Aaron Chan ⋅ Filip Ilievski ⋅ Muhao Chen ⋅ Xiang Ren
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
Jimmy Di ⋅ Jack Douglas ⋅ Jayadev Acharya ⋅ Gautam Kamath ⋅ Ayush Sekhari
Individual Privacy Accounting with Gaussian Differential Privacy
Antti Koskela ⋅ Marlon Tobaben ⋅ Antti Honkela
Distributed Differential Privacy in Multi-Armed Bandits
Sayak Ray Chowdhury ⋅ Xingyu Zhou
Explainability in Practice: Estimating Electrification Rates from Mobile Phone Data in Senegal
Laura State ⋅ Hadrien Salat ⋅ Stefania Rubrichi ⋅ Zbigniew Smoreda
Strategy-Aware Contextual Bandits
Keegan Harris ⋅ Chara Podimata ⋅ Steven Wu
Group Excess Risk Bound of Overparameterized Linear Regression with Constant-Stepsize SGD
Arjun Subramonian ⋅ Levent Sagun ⋅ Kai-Wei Chang ⋅ Yizhou Sun
Certified Training: Small Boxes are All You Need
Mark Müller ⋅ Franziska Eckert ⋅ Marc Fischer ⋅ Martin Vechev
Evaluating the Practicality of Counterfactual Explanation
Nina Spreitzer ⋅ Hinda Haned ⋅ Ilse van der Linden
A Deep Dive into Dataset Imbalance and Bias in Face Identification
Valeriia Cherepanova ⋅ Steven Reich ⋅ Samuel Dooley ⋅ Hossein Souri ⋅ John Dickerson ⋅ Micah Goldblum ⋅ Tom Goldstein
Differentially Private Gradient Boosting on Linear Learners for Tabular Data
Saeyoung Rho ⋅ Shuai Tang ⋅ Sergul Aydore ⋅ Michael Kearns ⋅ Aaron Roth ⋅ Yu-Xiang Wang ⋅ Steven Wu ⋅ Cedric Archambeau
TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations
Dylan Slack ⋅ Satyapriya Krishna ⋅ Himabindu Lakkaraju ⋅ Sameer Singh
Participatory Systems for Personalized Prediction
Hailey James ⋅ Chirag Nagpal ⋅ Katherine Heller ⋅ Berk Ustun
On the Impact of Adversarially Robust Models on Algorithmic Recourse
Satyapriya Krishna ⋅ Chirag Agarwal ⋅ Himabindu Lakkaraju
What Makes a Good Explanation?: A Unified View of Properties of Interpretable ML
Zixi Chen ⋅ Varshini Subhash ⋅ Marton Havasi ⋅ Weiwei Pan ⋅ Finale Doshi-Velez
REGLO: Provable Neural Network Repair for Global Robustness Properties
Feisi Fu ⋅ Zhilu Wang ⋅ Jiameng Fan ⋅ Yixuan Wang ⋅ Chao Huang ⋅ Xin Chen ⋅ Qi Zhu ⋅ Wenchao Li
A View From Somewhere: Human-Centric Face Representations
Jerone Andrews ⋅ Przemyslaw Joniak ⋅ Alice Xiang
On Causal Rationalization
Wenbo Zhang ⋅ TONG WU ⋅ Yunlong Wang ⋅ Yong Cai ⋅ Hengrui Cai
On the Importance of Architectures and Hyperparameters for Fairness in Face Recognition
Samuel Dooley ⋅ Rhea Sukthanker ⋅ John Dickerson ⋅ Colin White ⋅ Frank Hutter ⋅ Micah Goldblum
Finding Safe Zones of Markov Decision Processes Policies
Michal Moshkovitz ⋅ Lee Cohen ⋅ Yishay Mansour
Indiscriminate Data Poisoning Attacks on Neural Networks
Yiwei Lu ⋅ Gautam Kamath ⋅ Yaoliang Yu
Hybrid-EDL: Improving Evidential Deep Learning for Uncertainty Quantification on Imbalanced Data
Tong Xia ⋅ Jing Han ⋅ Lorena Qendro ⋅ Ting Dang ⋅ Cecilia Mascolo
Bias Amplification in Image Classification
Melissa Hall ⋅ Laurens van der Maaten ⋅ Laura Gustafson ⋅ Maxwell Jones ⋅ Aaron Adcock
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation
Maksym Yatsura ⋅ Kaspar Sakmann ⋅ N. Grace Hua ⋅ Matthias Hein ⋅ Jan Hendrik Metzen
Cold Posteriors through PAC-Bayes
Konstantinos Pitas ⋅ Julyan Arbel
Men Also Do Laundry: Multi-Attribute Bias Amplification
Dora Zhao ⋅ Jerone Andrews ⋅ Alice Xiang
Anonymization for Skeleton Action Recognition
Saemi Moon ⋅ Myeonghyeon Kim ⋅ Zhenyue Qin ⋅ Yang Liu ⋅ Dongwoo Kim
Provable Re-Identification Privacy
Zachary Izzo ⋅ Jinsung Yoon ⋅ Sercan Arik ⋅ James Zou
Attack-Agnostic Adversarial Detection
Jiaxin Cheng ⋅ Mohamed Hussein ⋅ Jayadev Billa ⋅ Wael Abd-Almageed
Visual Prompting for Adversarial Robustness
Aochuan Chen ⋅ Peter Lorenz ⋅ Yuguang Yao ⋅ Pin-Yu Chen ⋅ Sijia Liu
When Fairness Meets Privacy: Fair Classification with Semi-Private Sensitive Attributes
Canyu Chen ⋅ Yueqing Liang ⋅ Xiongxiao Xu ⋅ Shangyu Xie ⋅ Yuan Hong ⋅ Kai Shu
Differentially Private Bias-Term only Fine-tuning of Foundation Models
Zhiqi Bu ⋅ Yu-Xiang Wang ⋅ Sheng Zha ⋅ George Karypis
On the Feasibility of Compressing Certifiably Robust Neural Networks
Pratik Vaishnavi ⋅ Veena Krish ⋅ Farhan Ahmed ⋅ Kevin Eykholt ⋅ Amir Rahmati
Towards Algorithmic Fairness in Space-Time: Filling in Black Holes
Cheryl Flynn ⋅ Aritra Guha ⋅ Subhabrata Majumdar ⋅ Divesh Srivastava ⋅ Zhengyi Zhou
Just Following AI Orders: When Unbiased People Are Influenced By Biased AI
Hammaad Adam ⋅ Aparna Balagopalan ⋅ Emily Alsentzer ⋅ Fotini Christia ⋅ Marzyeh Ghassemi
Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge
ZIYUN LI ⋅ Xinshao Wang ⋅ Christoph Meinel ⋅ Neil Robertson ⋅ David Clifton ⋅ Haojin Yang
Scalable and Improved Algorithms for Individually Fair Clustering
Mohammadhossein Bateni ⋅ Vincent Cohen-Addad ⋅ Alessandro Epasto ⋅ Silvio Lattanzi
Membership Inference Attacks via Adversarial Examples
Hamid Jalalzai ⋅ Elie Kadoche ⋅ Rémi Leluc ⋅ Vincent Plassier
Take 5: Interpretable Image Classification with a Handful of Features
Thomas Norrenbrock ⋅ Marco Rudolph ⋅ Bodo Rosenhahn