Timezone: »

Multi-Objective GFlowNets
Moksh Jain · Sharath Chandra Raparthy · Alex Hernandez-Garcia · Jarrid Rector-Brooks · Yoshua Bengio · Santiago Miret · Emmanuel Bengio

Tue Jul 25 05:00 PM -- 06:30 PM (PDT) @ Exhibit Hall 1 #726
Event URL: https://github.com/GFNOrg/multi-objective-gfn »

We study the problem of generating diverse candidates in the context of Multi-Objective Optimization. In many applications of machine learning such as drug discovery and material design, the goal is to generate candidates which simultaneously optimize a set of potentially conflicting objectives. Moreover, these objectives are often imperfect evaluations of some underlying property of interest, making it important to generate diverse candidates to have multiple options for expensive downstream evaluations. We propose Multi-Objective GFlowNets (MOGFNs), a novel method for generating diverse Pareto optimal solutions, based on GFlowNets. We introduce two variants of MOGFNs: MOGFN-PC, which models a family of independent sub-problems defined by a scalarization function, with reward-conditional GFlowNets, and MOGFN-AL, which solves a sequence of sub-problems defined by an acquisition function in an active learning loop. Our experiments on wide variety of synthetic and benchmark tasks demonstrate advantages of the proposed methods in terms of the Pareto performance and importantly, improved candidate diversity, which is the main contribution of this work.

Author Information

Moksh Jain (Mila / Université de Montréal)
Sharath Chandra Raparthy (Facebook)
Alex Hernandez-Garcia (Mila - Quebec AI Institute)
Jarrid Rector-Brooks (Mila, Universite de Montreal)
Yoshua Bengio (Mila - Quebec AI Institute)
Santiago Miret (Intel Labs)
Emmanuel Bengio (McGill University)

More from the Same Authors