In real-world federated learning scenarios, participants could have their own personalized labels which are incompatible with those from other clients, due to using different label permutations or tackling completely different tasks or domains. However, most existing FL approaches cannot effectively tackle such extremely heterogeneous scenarios since they often assume that (1) all participants use a synchronized set of labels, and (2) they train on the same task from the same domain. In this work, to tackle these challenges, we introduce Factorized-FL, which allows to effectively tackle label-and task-heterogeneous federated learning settings by factorizing the model parameters into a pair of vectors, where one captures the common knowledge across different labels and tasks and the other captures knowledge specific to the task each local model tackles. Moreover, based on the distance in the client-specific vector space, Factorized-FL performs selective aggregation scheme to utilize only the knowledge from the relevant participants for each client. We extensively validate our method on both labeland domain-heterogeneous settings, on which it outperforms the state-of-the-art personalized federated learning methods.
In real-world scenarios, subgraphs of a larger global graph may be distributed across multiple devices or institutions, and only locally accessible due to privacy restrictions, although there may be links between them. Recently proposed subgraph Federated Learning (FL) methods deal with those missing links across private local subgraphs while distributively training Graph Neural Networks (GNNs) on them. However, they have overlooked the inevitable heterogeneity among subgraphs, caused by subgraphs comprising different parts of a global graph. For example, a subgraph may belong to one of the communities within the larger global graph. A naive subgraph FL in such a case will collapse incompatible knowledge from local GNN models trained on heterogeneous graph distributions. To overcome such a limitation, we introduce a new subgraph FL problem, personalized subgraph FL, which focuses on the joint improvement of the interrelated local GNN models rather than learning a single global GNN model, and propose a novel framework, FEDerated Personalized sUBgraph learning (FED-PUB), to tackle it. A crucial challenge in personalized subgraph FL is that the server does not know which subgraph each client has. FED-PUB thus utilizes functional embeddings of the local GNNs using random graphs as inputs to compute similarities between them, and use them to perform weighted averaging for server-side aggregation. Further, it learns a personalized sparse mask at each client to select and update only the subgraph-relevant subset of the aggregated parameters. We validate FED-PUB for its subgraph FL performance on six datasets, considering both non-overlapping and overlapping subgraphs, on which ours largely outperforms relevant baselines. * Equal contribution Preprint. Under review.
Because of the limits input/output systems currently impose on high-performance computing systems, a new generation of workflows that include online data reduction and analysis is emerging. Diagnosing their performance requires sophisticated performance analysis capabilities due to the complexity of execution patterns and underlying hardware, and no tool could handle the voluminous performance trace data needed to detect potential problems. This work introduces Chimbuko, a performance analysis framework that provides real-time, distributed, in situ anomaly detection. Data volumes are reduced for human-level processing without losing necessary details. Chimbuko supports online performance monitoring via a visualization module that presents the overall workflow anomaly distribution, call stacks, and timelines. Chimbuko also supports the capture and reduction of performance provenance. To the best of our knowledge, Chimbuko is the first online, distributed, and scalable workflowlevel performance trace analysis framework, and we demonstrate the tool's usefulness on Oak Ridge National Laboratory's Summit system.
In practical federated learning scenarios, the participating devices may have different bitwidths for computation and memory storage by design. However, despite the progress made in deviceheterogeneous federated learning scenarios, the heterogeneity in the bitwidth specifications in the hardware has been mostly overlooked. We introduce a pragmatic FL scenario with bitwidth heterogeneity across the participating devices, dubbed as Bitwidth Heterogeneous Federated Learning (BHFL). BHFL brings in a new challenge, that the aggregation of model parameters with different bitwidths could result in severe performance degeneration, especially for highbitwidth models. To tackle this problem, we propose ProWD framework, which has a trainable weight dequantizer at the central server that progressively reconstructs the low-bitwidth weights into higher bitwidth weights, and finally into fullprecision weights. ProWD further selectively aggregates the model parameters to maximize the compatibility across bit-heterogeneous weights. We validate ProWD against relevant FL baselines on the benchmark datasets, using clients with varying bitwidths. Our ProWD largely outperforms the baseline FL algorithms as well as naive approaches (e.g. grouped averaging) under the proposed BHFL scenario.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.