{"ID":5438728,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T08:21:40.02248845Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31331","arxiv_id":"2606.31331","title":"Expected Gain-based Escalation in Vertical Federated Learning","abstract":"Collaborative inference can improve predictive performance by integrating complementary information across agents, but applying collaborative fusion to every sample can incur unnecessary communication and computational overhead. This trade-off is particularly relevant in vertical federated learning (VFL), where clients observe different views of the same sample and fusion typically requires transmitting intermediate representations to a server. We study selective escalation in a two-round VFL inference protocol, in which a low-cost first round produces a prediction from client posteriors and a second embedding-fusion round is invoked only when it is expected to improve the final decision. We formulate routing as expected-gain score estimation: a sample is escalated when a predicted improvement in correctness justifies the additional communication. The proposed analytical score combines a calibrated pooled posterior with classwise reliability estimates of the VFL model, both obtained from held-out calibration data, yielding an interpretable router that requires no separately trained routing network. Experiments on multi-view classification benchmarks, including controlled test--time view degradation settings, show that the proposed router improves the communication-accuracy trade-off over confidence-, learned-gain-, and deferral-based baselines.","short_abstract":"Collaborative inference can improve predictive performance by integrating complementary information across agents, but applying collaborative fusion to every sample can incur unnecessary communication and computational overhead. This trade-off is particularly relevant in vertical federated learning (VFL), where clients...","url_abs":"https://arxiv.org/abs/2606.31331","url_pdf":"https://arxiv.org/pdf/2606.31331v1","authors":"[\"Mohamad Mestoukirdi\",\"Vincent Corlay\"]","published":"2026-06-30T08:32:53Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}