Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379473246> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4379473246 abstract "Learning an effective global model on private and decentralized datasets has become an increasingly important challenge of machine learning when applied in practice. Existing distributed learning paradigms, such as Federated Learning, enable this via model aggregation which enforces a strong form of modeling homogeneity and synchronicity across clients. This is however not suitable to many practical scenarios. For example, in distributed sensing, heterogeneous sensors reading data from different views of the same phenomenon would need to use different models for different data modalities. Local learning therefore happens in isolation but inference requires merging the local models to achieve consensus. To enable consensus among local models, we propose a feature fusion approach that extracts local representations from local models and incorporates them into a global representation that improves the prediction performance. Achieving this requires addressing two non-trivial problems. First, we need to learn an alignment between similar feature components which are arbitrarily arranged across clients to enable representation aggregation. Second, we need to learn a consensus graph that captures the high-order interactions between local feature spaces and how to combine them to achieve a better prediction. This paper presents solutions to these problems and demonstrates them in real-world applications on time series data such as power grids and traffic networks." @default.
- W4379473246 created "2023-06-07" @default.
- W4379473246 creator A5010479652 @default.
- W4379473246 creator A5035602232 @default.
- W4379473246 creator A5086690079 @default.
- W4379473246 date "2023-06-01" @default.
- W4379473246 modified "2023-09-30" @default.
- W4379473246 title "Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs" @default.
- W4379473246 doi "https://doi.org/10.48550/arxiv.2306.01240" @default.
- W4379473246 hasPublicationYear "2023" @default.
- W4379473246 type Work @default.
- W4379473246 citedByCount "0" @default.
- W4379473246 crossrefType "posted-content" @default.
- W4379473246 hasAuthorship W4379473246A5010479652 @default.
- W4379473246 hasAuthorship W4379473246A5035602232 @default.
- W4379473246 hasAuthorship W4379473246A5086690079 @default.
- W4379473246 hasBestOaLocation W43794732461 @default.
- W4379473246 hasConcept C119857082 @default.
- W4379473246 hasConcept C124101348 @default.
- W4379473246 hasConcept C132525143 @default.
- W4379473246 hasConcept C138885662 @default.
- W4379473246 hasConcept C154945302 @default.
- W4379473246 hasConcept C17744445 @default.
- W4379473246 hasConcept C199539241 @default.
- W4379473246 hasConcept C2776214188 @default.
- W4379473246 hasConcept C2776359362 @default.
- W4379473246 hasConcept C2776401178 @default.
- W4379473246 hasConcept C41008148 @default.
- W4379473246 hasConcept C41895202 @default.
- W4379473246 hasConcept C59404180 @default.
- W4379473246 hasConcept C80444323 @default.
- W4379473246 hasConcept C94625758 @default.
- W4379473246 hasConceptScore W4379473246C119857082 @default.
- W4379473246 hasConceptScore W4379473246C124101348 @default.
- W4379473246 hasConceptScore W4379473246C132525143 @default.
- W4379473246 hasConceptScore W4379473246C138885662 @default.
- W4379473246 hasConceptScore W4379473246C154945302 @default.
- W4379473246 hasConceptScore W4379473246C17744445 @default.
- W4379473246 hasConceptScore W4379473246C199539241 @default.
- W4379473246 hasConceptScore W4379473246C2776214188 @default.
- W4379473246 hasConceptScore W4379473246C2776359362 @default.
- W4379473246 hasConceptScore W4379473246C2776401178 @default.
- W4379473246 hasConceptScore W4379473246C41008148 @default.
- W4379473246 hasConceptScore W4379473246C41895202 @default.
- W4379473246 hasConceptScore W4379473246C59404180 @default.
- W4379473246 hasConceptScore W4379473246C80444323 @default.
- W4379473246 hasConceptScore W4379473246C94625758 @default.
- W4379473246 hasLocation W43794732461 @default.
- W4379473246 hasOpenAccess W4379473246 @default.
- W4379473246 hasPrimaryLocation W43794732461 @default.
- W4379473246 hasRelatedWork W2546942002 @default.
- W4379473246 hasRelatedWork W2573132524 @default.
- W4379473246 hasRelatedWork W2768413403 @default.
- W4379473246 hasRelatedWork W2963058055 @default.
- W4379473246 hasRelatedWork W3003242282 @default.
- W4379473246 hasRelatedWork W3087493185 @default.
- W4379473246 hasRelatedWork W3128070591 @default.
- W4379473246 hasRelatedWork W3136048210 @default.
- W4379473246 hasRelatedWork W4281760909 @default.
- W4379473246 hasRelatedWork W4319452631 @default.
- W4379473246 isParatext "false" @default.
- W4379473246 isRetracted "false" @default.
- W4379473246 workType "article" @default.