Multi-Objective GFlowNets

by   Moksh Jain, et al.

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, in practice, these objectives are often under-specified, making the diversity of candidates a key consideration. The existing multi-objective optimization methods focus predominantly on covering the Pareto front, failing to 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 novel 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 and benchmark tasks, 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.


page 18

page 22


Multi-Objective Quality Diversity Optimization

In this work, we consider the problem of Quality-Diversity (QD) optimiza...

Evolutionary Multi-Objective Design of SARS-CoV-2 Protease Inhibitor Candidates

Computational drug design based on artificial intelligence is an emergin...

Assessing the Frontier: Active Learning, Model Accuracy, and Multi-objective Materials Discovery and Optimization

Discovering novel materials can be greatly accelerated by iterative mach...

Visualization of Multi-Objective Switched Reluctance Machine Optimization at Multiple Operating Conditions with t-SNE

The optimization of electric machines at multiple operating points is cr...

Enhanced Optimization with Composite Objectives and Novelty Selection

An important benefit of multi-objective search is that it maintains a di...

Multicriteria asset allocation in practice

In this paper we consider the strategic asset allocation of an insurance...

Mind the Gap: Measuring Generalization Performance Across Multiple Objectives

Modern machine learning models are often constructed taking into account...

Please sign up or login with your details

Forgot password? Click here to reset