Multi-Objective Coverage via Constraint Active Search

TL;DR

This paper introduces a new multi-objective coverage problem and proposes an active search algorithm, MOC-CAS, to efficiently identify representative samples that broadly cover the feasible multi-objective space, accelerating scientific discovery.

Contribution

The paper formulates the multi-objective coverage problem and develops MOC-CAS, a novel active search method using Gaussian processes and a relaxed feasibility test for efficient sampling.

Findings

MOC-CAS outperforms baseline methods in large-scale protein datasets.

It achieves broader coverage of the multi-objective space.

Demonstrates effectiveness in drug discovery-related tasks.

Abstract

In this paper, we formulate the new multi-objective coverage (MOC) problem where our goal is to identify a small set of representative samples whose predicted outcomes broadly cover the feasible multi-objective space. This problem is of great importance in many critical real-world applications, e.g., drug discovery and materials design, as this representative set can be evaluated much faster than the whole feasible set, thus significantly accelerating the scientific discovery process. Existing works cannot be directly applied as they either focus on sample space coverage or multi-objective optimization that targets the Pareto front. However, chemically diverse samples often yield identical objective profiles, and safety constraints are usually defined on the objectives. To solve this MOC problem, we propose a novel search algorithm, MOC-CAS, which employs an upper confidence bound-based acquisition function to select optimistic samples guided by Gaussian process posterior predictions. For enabling efficient optimization, we develop a smoothed relaxation of the hard feasibility test and derive an approximate optimizer. Compared to the competitive baselines, we show that our MOC-CAS empirically achieves superior performances across large-scale protein-target datasets for SARS-CoV-2 and cancer, each assessed on five objectives derived from SMILES-based features.