Michael Zhang

TL;DR: This work efficiently calculate optimal weighted model combinations for each client, based on figuring out how much a client can benefit from another's model, to achieve personalization in federated FL.

TL;DR: The authors provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e. g.g. model architectures, training procedures, data, systems, security, evaluation, theory) to their applications.

TL;DR: A simple way to modify any conventional deep architecture to automatically provide more transparent explanations for classification decisions, as well as an intuitive notion of the credibility of each prediction is proposed, drawing on ideas from nonparametric kernel regression.

TL;DR: In this paper, each client only federates with other relevant clients to obtain a stronger model per client-specific objectives, rather than computing a single model average with constant weights for the entire federation as in traditional FL, the authors efficiently calculate optimal weighted model combinations for each client, based on figuring out how much a client can benefit from another's model.

TL;DR: This article proposed to predict labels based on a weighted sum of training instances, where the weights are determined by distance in a learned instance-embedding space, and experimentally validate the accompanying theoretical expectations, demonstrating improved transparency, controlled error rates, and robustness to out-of-domain data.