@article {pub6342,
	title = {Pruning Federated Models through Loss Landscape Analysis and Client Agreement Scoring},
	author = {Christian Intern{\'o} AND Elena Raponi AND Markus Olhofer AND Ali Raza AND Thomas B{\"a}ck AND Niki van Stein AND Yaochu Jin AND Barbara Hammer},
	year = {2026},
	month = {April},
	abstract = {The practical deployment of Federated Learning (FL) on resource-constrained devices is fundamentally limited by the high cost of training large models and the instability caused by heterogeneous (non-IID) client data. Conventional pruning methods often treat data heterogeneity as a problem to be mitigated. In this work, we introduce a paradigm shift: we reframe client diversity as a feature to be harnessed. We propose AutoFLIP, a framework that begins not with training, but with a one-time federated loss exploration. During this phase, clients collaboratively build a map of the collective loss landscape, using their diverse data to reveal the problem{\textquoteright}s essential structure. This shared intelligence then guides an adaptive pruning strategy that is dynamically refined by client agreement throughout training. This approach allows AutoFLIP to identify robust and efficient sub-networks from the outset. Our extensive experiments show that AutoFLIP reduces computational overhead by an average of 52\% and communication costs by over 65\% while simultaneously achieving state-of-the-art accuracy in challenging non-IID settings.},
	publisher = {IEEE},
	journal = {IEEE Internet of Things Journal}
}