Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design

TL;DR

This paper introduces goal-conditioned GFlowNets for multi-objective molecular design, enabling more controllable and uniform exploration of solutions across the entire Pareto front, addressing limitations of scalarization methods.

Contribution

It proposes a novel goal-conditioned GFlowNet approach for molecular design, improving control and diversity in multi-objective optimization compared to scalarization techniques.

Findings

Enhanced ability to explore the entire Pareto front.

More controllable molecular generation across multiple objectives.

Addresses limitations of scalarization in multi-objective optimization.

Abstract

In recent years, in-silico molecular design has received much attention from the machine learning community. When designing a new compound for pharmaceutical applications, there are usually multiple properties of such molecules that need to be optimised: binding energy to the target, synthesizability, toxicity, EC50, and so on. While previous approaches have employed a scalarization scheme to turn the multi-objective problem into a preference-conditioned single objective, it has been established that this kind of reduction may produce solutions that tend to slide towards the extreme points of the objective space when presented with a problem that exhibits a concave Pareto front. In this work we experiment with an alternative formulation of goal-conditioned molecular generation to obtain a more controllable conditional model that can uniformly explore solutions along the entire Pareto front.