Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints

arXiv stat.ML / 4/23/2026

💬 OpinionDeveloper Stack & InfrastructureModels & Research

共有:

Key Points

The paper proposes a Decision-Focused Federated Learning (DFFL) framework where clients train predictive models that are used in downstream linear optimization problems without sharing raw data.
It extends the SPO+ surrogate-loss approach to settings with heterogeneous client objectives and feasibility constraints, deriving heterogeneity bounds using support-function representations and separating objective-shift vs feasible-set-shift effects.
For strongly convex feasible regions, the authors obtain sharper theoretical bounds thanks to optimizer stability.
They introduce a heuristic local-versus-federated decision rule showing that federation improves decision quality when the heterogeneity penalty is outweighed by the statistical benefit of pooling data.
Experiments with a FedAvg-style DFFL implementation indicate robust performance in strongly convex problems, while degradation in polyhedral problems is driven mainly by constraint heterogeneity (notably for clients with more samples).

Abstract

We consider what we refer to as {Decision-Focused Federated Learning (DFFL)} framework, i.e., a predict-then-optimize approach employed by a collection of agents, where each agent's predictive model is an input to a downstream linear optimization problem, and no direct exchange of raw data is allowed. Importantly, clients can differ both in objective functions and in feasibility constraints. We build on the well-known SPO+ approach and develop heterogeneity bounds for the SPO+ surrogate loss in this case. This is accomplished by employing a support function representation of the feasible region, separating (i) objective shift via norm distances between the cost vectors and (ii) feasible-set shift via shape distances between the constraint sets. In the case of strongly convex feasible regions, sharper bounds are derived due to the optimizer stability. Building on these results, we define a heuristic local-versus-federated excess risk decision rule which, under SPO+ risk, gives a condition for when federation can be expected to improve decision quality: the heterogeneity penalty must be smaller than the statistical advantage of pooling data. We implement a FedAvg-style DFFL set of experiments on both polyhedral and strongly convex problems and show that federation is broadly robust in the strongly convex setting, while performance in the polyhedral setting degrades primarily with constraint heterogeneity, especially for clients with many samples. In other words, especially for the strongly convex case, an approach following a direct implementation of FedAvg and SPO+ can still yield promising performance even when the downstream optimization problems are noticeably different.