Skip to yearly menu bar Skip to main content


Workshop

Pitfalls of limited data and computation for Trustworthy ML

Amartya Sanyal ⋅ Alexandru Tifrea ⋅ Ankit Pensia ⋅ Franziska Boenisch ⋅ Varun Kanade ⋅ Fanny Yang ⋅ Prateek Jain ⋅ Sara Hooker ⋅ Jamie Morgenstern
Project Page

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
1:25 AM
Beyond Confidence: Reliable Models Should Also Quantify Atypicality (Oral)
Mert Yuksekgonul ⋅ Linjun Zhang ⋅ James Y Zou ⋅ Carlos Guestrin
1:35 AM
On the Efficacy of Differentially Private Few-shot Image Classification (Oral)
Marlon Tobaben ⋅ Aliaksandra Shysheya ⋅ John Bronskill ⋅ Andrew Paverd ⋅ Shruti Tople ⋅ Santiago Zanella-Beguelin ⋅ Richard E Turner ⋅ Antti Honkela
1:55 AM
Error Discovery by Clustering Influence Embeddings (Oral)
Fulton Wang ⋅ Julius Adebayo ⋅ Sarah Tan ⋅ Diego Garcia-Olano ⋅ Narine Kokhlikyan
2:05 AM
Coffee Break
2:15 AM
Poster Session
3:15 AM
Lunch Break
6:25 AM
Coffee Break
7:05 AM
Project with Source, Probe with Target: Extracting Useful Features for Adaptation to Distribution Shifts (Oral)
Annie Chen ⋅ Yoonho Lee ⋅ Amrith Setlur ⋅ Sergey Levine ⋅ Chelsea Finn
7:15 AM
Efficient Utilization of Pre-Trained Model for Learning with Noisy Labels (Oral)
Jongwoo Ko ⋅ Sumyeong Ahn ⋅ Se-Young Yun
7:25 AM
Closing Remarks
7:30 AM
Poster Session
DORA: Exploring outlier representations in Deep Neural Networks
Kirill Bykov ⋅ Mayukh Deb ⋅ Dennis Grinwald ⋅ Klaus R Muller ⋅ Marina Höhne
GeValDi: Generative Validation of Discriminative Models
Vivek Palaniappan ⋅ Matthew Ashman ⋅ Katherine Collins ⋅ Juyeon Heo ⋅ Adrian Weller ⋅ Umang Bhatt
On Gradients of Deep Generative Models for Representation-Invariant Anomaly Detection
Sam Dauncey ⋅ Christopher Holmes ⋅ Christopher Williams ⋅ Fabian Falck
Training, Architecture, and Prior for Deterministic Uncertainty Methods
Bertrand Charpentier ⋅ Chenxiang Zhang ⋅ Stephan Günnemann
Fairness-Aware Data Valuation for Supervised Learning
José Pombal ⋅ Pedro Saleiro ⋅ Mario Figueiredo ⋅ Pedro Bizarro
KNIFE: Distilling Meta-Reasoning Knowledge with Free-Text Rationales
Aaron Chan ⋅ Zhiyuan Zeng ⋅ Wyatt Lake ⋅ Brihi Joshi ⋅ Hanjie Chen ⋅ Xiang Ren
Privately Customizing Prefinetuning to Better Match User Data in Federated Learning
Charlie Hou ⋅ Hongyuan Zhan ⋅ Akshat Shrivastava ⋅ Sid Wang ⋅ Aleksandr Livshits ⋅ Giulia Fanti ⋅ Daniel Lazar
Robustifying Language Models with Test-Time Adaptation
Noah McDermott ⋅ Junfeng Yang ⋅ Chengzhi Mao
Pitfalls in Evaluating GNNs under Label Poisoning Attacks
Vijay Chandra Lingam ⋅ Mohammad Sadegh Akhondzadeh ⋅ Aleksandar Bojchevski
Enabling Calibration In The Zero-Shot Inference of Large Vision-Language Models
Will LeVine ⋅ Benjamin Pikus ⋅ Pranav Raja ⋅ Fernando Amat
Label Calibration for Semantic Segmentation Under Domain Shift
Ondrej Bohdal ⋅ Da Li ⋅ Timothy Hospedales
Feature-Interpretable Real Concept Drift Detection
Pranoy Panda ⋅ Vineeth Balasubramanian ⋅ Gaurav Sinha
Mark My Words: Dangers of Watermarked Images in ImageNet
Kirill Bykov ⋅ Klaus R Muller ⋅ Marina Höhne
Do Models see Corruption as we see? An Item Response Theory based study in Computer Vision
Charchit Sharma ⋅ Ayan Pahari ⋅ Deepak Vijaykeerthy ⋅ Vineeth Balasubramanian
Concept discovery and Dataset exploration with Singular Value Decomposition
Mara Graziani ⋅ An-phi Nguyen ⋅ Laura O'Mahony ⋅ Henning Müller ⋅ Vincent Andrearczyk
Distribution Aware Active Learning via Gaussian Mixtures
Younghyun Park ⋅ Dong-Jun Han ⋅ Jungwuk Park ⋅ Wonjeong Choi ⋅ Humaira Kousar ⋅ Jaekyun Moon
Understanding the class-specific effects of data augmentations
Polina Kirichenko ⋅ Randall Balestriero ⋅ Mark Ibrahim ⋅ Shanmukha Ramakrishna Vedantam ⋅ Hamed Firooz ⋅ Andrew Wilson
Identifying Incorrect Annotations in Multi-label Classification Data
Aditya Thyagarajan ⋅ Elias Snorrason ⋅ Curtis Northcutt ⋅ Jonas Mueller
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation
Julian Bitterwolf ⋅ Maximilian Müller ⋅ Matthias Hein
Robust Neural Architecture Search by Cross-Layer Knowledge Distillation
Utkarsh Nath ⋅ Yancheng Wang ⋅ Yingzhen Yang
Learning with Explanation Constraints
Rattana Pukdee ⋅ Dylan Sam ⋅ Zico Kolter ⋅ Nina Balcan ⋅ Pradeep K Ravikumar
Predicting Out-of-Distribution Error with Confidence Optimal Transport
Yuzhe Lu ⋅ Zhenlin Wang ⋅ Runtian Zhai ⋅ Soheil Kolouri ⋅ Joseph Campbell ⋅ Katia Sycara
Max-margin Inspired Per-sample Re-weighting for Robust Deep Learning
Ramnath Kumar ⋅ Kushal Majmundar ⋅ Dheeraj Nagaraj ⋅ Arun Suggala
Superhuman Fairness
Omid Memarrast ⋅ Trong Linh Vu ⋅ Brian Ziebart
A Case Study on Designing Evaluations of ML Explanations with Simulated User Studies
Ada Martin ⋅ Valerie Chen ⋅ Sérgio Jesus ⋅ Pedro Saleiro
Reconstructing Training Data from Multiclass Neural Networks
Gon Buzaglo ⋅ Niv Haim ⋅ Gilad Yehudai ⋅ Gal Vardi ⋅ michal Irani
Self-Consistent Chain-of-Thought Distillation
Peifeng Wang ⋅ Zhengyang Wang ⋅ Zheng Li ⋅ Yifan Gao ⋅ Bing Yin ⋅ Xiang Ren
FEDERATED TRAINING OF DUAL ENCODING MODELS ON SMALL NON-IID CLIENT DATASETS
Raviteja Vemulapalli ⋅ Warren Morningstar ⋅ Philip Mansfield ⋅ Hubert Eichner ⋅ Karan Singhal ⋅ Arash Afkanpour ⋅ Bradley Green
On Pitfalls of Test-Time Adaptation
Hao Zhao ⋅ Yuejiang Liu ⋅ Alexandre Alahi ⋅ Tao Lin
Conservative Prediction via Transductive Confidence Minimization
Caroline Choi ⋅ Fahim Tajwar ⋅ Yoonho Lee ⋅ Huaxiu Yao ⋅ Ananya Kumar ⋅ Chelsea Finn
Differentially Private Federated Few-shot Image Classification
Aliaksandra Shysheya ⋅ Marlon Tobaben ⋅ John Bronskill ⋅ Andrew Paverd ⋅ Shruti Tople ⋅ Santiago Zanella-Beguelin ⋅ Richard E Turner ⋅ Antti Honkela
Zero redundancy distributed learning with differential privacy (Oral)
Zhiqi Bu ⋅ Justin Chiu ⋅ Ruixuan Liu ⋅ Yu-Xiang Wang ⋅ Sheng Zha ⋅ George Karypis
How to Make Semi-Private Learning Effective
Francesco Pinto ⋅ Yaxi Hu ⋅ Fanny Yang ⋅ Amartya Sanyal
Project with Source, Probe with Target: Extracting Useful Features for Adaptation to Distribution Shifts
Annie Chen ⋅ Yoonho Lee ⋅ Amrith Setlur ⋅ Sergey Levine ⋅ Chelsea Finn
Beyond Confidence: Reliable Models Should Also Quantify Atypicality
Mert Yuksekgonul ⋅ Linjun Zhang ⋅ James Y Zou ⋅ Carlos Guestrin
On the Efficacy of Differentially Private Few-shot Image Classification
Marlon Tobaben ⋅ Aliaksandra Shysheya ⋅ John Bronskill ⋅ Shruti Tople ⋅ Santiago Zanella-Beguelin ⋅ Richard E Turner ⋅ Antti Honkela
Error Discovery by Clustering Influence Embeddings
Fulton Wang ⋅ Julius Adebayo ⋅ Sarah Tan ⋅ Diego Garcia-Olano ⋅ Narine Kokhlikyan