Pair-matching: Link prediction with adaptive queries

  • Christophe Giraud

    Université Paris-Saclay, CNRS, Orsay, France
  • Yann Issartel

    Université Paris-Saclay, CNRS, Orsay, France; Institut Polytechnique de Paris, Palaiseau, France
  • Luc Lehéricy

    Université Paris-Saclay, CNRS, Orsay, France; Université Côte d’Azur, Nice, France
  • Matthieu Lerasle

    CNRS, École polytechnique, GENES, ENSAE Paris, Institut Polytechnique de Paris, Palaiseau, France
Pair-matching: Link prediction with adaptive queries cover
Download PDF

This article is published open access under our Subscribe to Open model.

Abstract

The pair-matching problem appears in many applications where one wants to discover matches between pairs of entities or individuals. Formally, the set of individuals is represented by the nodes of a graph where the edges, unobserved at first, represent the matches. The algorithm queries pairs of nodes and observes the presence/absence of edges. Its goal is to discover as many edges as possible with a fixed budget of queries. Pair-matching is a particular instance of multi-armed bandit problem in which the arms are pairs of individuals and the rewards are edges linking these pairs. This bandit problem is non-standard though, as each arm can only be played once.
Given this last constraint, sublinear regret can be expected only if the graph presents some underlying structure. This paper shows that sublinear regret is achievable in the case where the graph is generated according to a stochastic block model (SBM) with two communities. Optimal regret bounds are computed for this pair-matching problem. They exhibit a phase transition related to the Kesten–Stigum threshold for community detection in SBM. The pair-matching problem is considered in the case where each node is constrained to be sampled less than a given amount of times, for example for ensuring individual fairness. We show how optimal regret rates depend on this constraint. The paper is concluded by a conjecture regarding the optimal regret when the number of communities is larger than . Contrary to the two communities case, we argue that a statistical-computational gap would appear in this problem.

Cite this article

Christophe Giraud, Yann Issartel, Luc Lehéricy, Matthieu Lerasle, Pair-matching: Link prediction with adaptive queries. Math. Stat. Learn. 7 (2024), no. 3/4, pp. 221–295

DOI 10.4171/MSL/46