Harald SackJul 26, 2023
Slides for the #icml2023 tutorial on "Trustworthy Generative AI" by Nazneen Rajani, Hima Lakkaraju, and Krishnaram Kenthapadi
Tutorial website: https://sites.google.com/view/responsible-gen-ai-tutorial
Slides: https://t.co/hNQMkXOqgZ
@nazneenrajani @ICMLConf #trust #trustworthyAI #AI #icml #icml2023
#icml23 #generativeAI
Responsible Generative AI Tutorial

Overview Artificial Intelligence (AI) based solutions are increasingly deployed in high-stakes domains such as healthcare, lending, hiring, criminal justice, and education, thereby transforming the way these industries operate and impacting individuals, businesses, and society as a whole.

UKRI AI for Healthcare CentresJul 26, 2023
AI4Health PhD @JoshSouthern13 is talking about his focus on graph neural networks #ICML23
Alex Hernandez-GarciaJul 25, 2023

If you are at #ICML23 and want to learn about GFlowNets or generative models for scientific discovery, go talk to my co-authors at the poster sessions today!

- A theory of continuous generative flow networks (11 am now!) https://arxiv.org/abs/2301.12594
- Multi-Objective GFlowNets (2 pm) https://arxiv.org/abs/2210.12765

A theory of continuous generative flow networks

Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target distributions over compositional objects. A key limitation of GFlowNets until this time has been that they are restricted to discrete spaces. We present a theory for generalized GFlowNets, which encompasses both existing discrete GFlowNets and ones with continuous or hybrid state spaces, and perform experiments with two goals in mind. First, we illustrate critical points of the theory and the importance of various assumptions. Second, we empirically demonstrate how observations about discrete GFlowNets transfer to the continuous case and show strong results compared to non-GFlowNet baselines on several previously studied tasks. This work greatly widens the perspectives for the application of GFlowNets in probabilistic inference and various modeling settings.

arXiv.org