Multi-Objective GFlowNets

Moksh Jain, Sharath Chandra Raparthy, Alex Hernández-García, Jarrid Rector-Brooks, Yoshua Bengio, Santiago Miret, Emmanuel Bengio

Keywords: generative flow networks, multi-objective optimization, drug discovery, material design

TL;DR: We generate diverse Pareto-optimal candidates for high-dimensional multi-objective optimization problems with GFlowNets.

Abstract: In many applications of machine learning, like drug discovery and material design, the goal is to generate candidates that simultaneously maximize a set of objectives. As these objectives are often conflicting, there is no single candidate that simultaneously maximizes all objectives, but rather a set of Pareto-optimal candidates where one objective cannot be improved without worsening another. Moreover, these objectives, when considered in practice are often under-specified, making diversity of candidates a key consideration. The existing multi-objective optimization methods focus predominantly on covering the Pareto front, failing the capture diversity in the space of candidates. Motivated by the success of GFlowNets for generation of diverse candidates in a single objective setting, in this paper we consider Multi-Objective GFlowNets (MOGFNs). MOGFNs consist of a Conditional GFlowNet which models a family of single-objective sub-problems derived by decomposing the multi-objective optimization problem. Our work is the first to empirically demonstrate conditional GFlowNets. Through a series of experiments on synthetic tasks and real-world domains, we empirically demonstrate that MOGFNs outperform existing methods in terms of Hypervolume, R2-distance and candidate diversity. We also demonstrate the effectiveness of MOGFNs over existing methods in active learning settings. Finally, we supplement our empirical results with a careful analysis of each component of MOGFNs.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Generative models

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/multi-objective-gflownets/code)