Thread by @hima_lakkaraju

Our group @ai4life_harvard is gearing up for showcasing our recent research and connecting with the #ML #TrustworthyML #XAI community at #NeurIPS2022. Here’s where you can find us at a glance. More details about our papers/talks/panels in the thread below 👇 [1/N]

@ai4life_harvard [Conference Paper] Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations (joint work with #TessaHan and @Suuraj) -- arxiv.org/abs/2206.01254. More details in this thread [2/N]

[Conference Paper] Efficient Training of Low-Curvature Neural Networks (joint work with @Suuraj, #KyleMatoba, @francoisfleuret) -- arxiv.org/abs/2206.07144. More details in this thread [3/N]

[Conference Paper] OpenXAI: Towards a Transparent Evaluation of Model Explanations (joint work w/ @_cagarwal, @SatyaXploringAI, @eshikasax, @MartinPawelczyk, @narijohnson, #Isha, @marinkazitnik) -- arxiv.org/abs/2206.11104. More details in this thread [4/N]

[Invited Talk/Panel] I will be giving a talk on "A Brief History of Explainable AI: From Simple Rules to Large Pretrained Models" & participating in a panel @WiMLworkshop. My talk will give a brief overview of #XAI while highlighting our work in it. sites.google.com/view/wiml2022/… [5/N]

[Invited Talk] I will be giving a talk on "Does Model Understanding Improve Clinical Decision Making" @SymposiumML4H. My talk will showcase our user studies with healthcare professionals on effectiveness of existing #XAI tools & their wishlists. ml4health.github.io/2022/ [6/N]

[Workshop Paper] On the Impact of Adversarially Robust Models on Algorithmic Recourse (joint work with @SatyaXploringAI @_cagarwal) at TSRML workshop -- openreview.net/forum?id=qnSsY…. TLDR: When models are adversarially robust, corresponding recourses will be harder to implement [7/N]

[Workshop Paper] Rethinking Explainability as a Dialogue: A Practitioner’s Perspective (joint w/ @dylanslack20 @yuxinch @ChenhaoTan @sameer_) at HCAI workshop -- arxiv.org/abs/2202.01875. More details in this thread [8/N]

[Workshop Paper] TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations (joint w/ @dylanslack20 @SatyaXploringAI @sameer_) at TSRML workshop -- arxiv.org/abs/2207.04154. More details in this thread [9/N]

We look forward to meeting everyone in the @trustworthy_ml @XAI_Research and the broader ML community at #NeurIPS2022 #WiMLNeurIPS2022 @WiMLworkshop, and chatting more about our research and learning more about yours! Please drop by to say hi :) [N/N]