960 citations · 3.4k across the 60 of their papers we have counts for
11 papers · 1 filter
Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
Thomas Hartvigsen, Swami Sankaranarayanan, Hamid Palangi +2
Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted…
"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts
Haoran Zhang, Harvineet Singh, Marzyeh Ghassemi +1
Machine learning models frequently experience performance drops under distribution shifts. The underlying cause of such shifts may be multiple simultaneous factors such as changes…
If Influence Functions are the Answer, Then What is the Question?
Juhan Bae, Nathan Ng, Alston Lo +2
Influence functions efficiently estimate the effect of removing a single training data point on a model's learned parameters. While influence estimates align well with leave-one-ou…
Predicting Out-of-Domain Generalization with Neighborhood Invariance
Nathan Ng, Neha Hulkund, Kyunghyun Cho +1
Developing and deploying machine learning models safely depends on the ability to characterize and compare their abilities to generalize to new environments. Although recent work h…
The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations
Aparna Balagopalan, Haoran Zhang, Kimia Hamidieh +3
Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc exp…
When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction
Vinith M. Suriyakumar, Marzyeh Ghassemi, Berk Ustun
Machine learning models are often personalized with categorical attributes that are protected, sensitive, self-reported, or costly to acquire. In this work, we show models that are…
Write It Like You See It: Detectable Differences in Clinical Notes By Race Lead To Differential Model Recommendations
Hammaad Adam, Ming Ying Yang, Kenrick Cato +6
Clinical notes are becoming an increasingly important data source for machine learning (ML) applications in healthcare. Prior research has shown that deploying ML models can perpet…
Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning
Natalie Dullerud, Karsten Roth, Kimia Hamidieh +2
Deep metric learning (DML) enables learning with less supervision through its emphasis on the similarity structure of representations. There has been much work on improving general…
Improving the Fairness of Chest X-ray Classifiers
Haoran Zhang, Natalie Dullerud, Karsten Roth +3
Deep learning models have reached or surpassed human-level performance in the field of medical imaging, especially in disease diagnosis using chest x-rays. However, prior work has…
Semi-Markov Offline Reinforcement Learning for Healthcare
Mehdi Fatemi, Mary Wu, Jeremy Petch +5
Reinforcement learning (RL) tasks are typically framed as Markov Decision Processes (MDPs), assuming that decisions are made at fixed time intervals. However, many applications of…
Learning Optimal Predictive Checklists
Haoran Zhang, Quaid Morris, Berk Ustun +1
Checklists are simple decision aids that are often used to promote safety and reliability in clinical applications. In this paper, we present a method to learn checklists for clini…