The More the Merrier - Federated Learning from Local Sphere Recommendations - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

The More the Merrier - Federated Learning from Local Sphere Recommendations

Bernd Malle
  • Function : Author
  • PersonId : 1022785
Peter Kieseberg
  • Function : Author
  • PersonId : 993469
Andreas Holzinger
  • Function : Author
  • PersonId : 1022786

Abstract

With Google’s Federated Learning & Facebook’s introduction of client-side NLP into their chat service, the era of client-side Machine Learning is upon us. While interesting ML approaches beyond the realm of toy examples were hitherto confined to large data-centers and powerful GPU’s, exponential trends in technology and the introduction of billions of smartphones enable sophisticated processing swarms of even hand-held devices. Such approaches hold several promises: 1. Without the need for powerful server infrastructures, even small companies could be scalable to millions of users easily and cost-efficiently; 2. Since data only used in the learning process never need to leave the client, personal information can be used free of privacy and data security concerns; 3. Since privacy is preserved automatically, the full range of personal information on the client device can be utilized for learning; and 4. without round-trips to the server, results like recommendations can be made available to users much faster, resulting in enhanced user experience. In this paper we propose an architecture for federated learning from personalized, graph based recommendations computed on client devices, collectively creating & enhancing a global knowledge graph. In this network, individual users will ‘train’ their local recommender engines, while a server-based voting mechanism aggregates the developing client-side models, preventing over-fitting on highly subjective data from tarnishing the global model.
Fichier principal
Vignette du fichier
456304_1_En_24_Chapter.pdf (762.74 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01677145 , version 1 (08-01-2018)

Licence

Attribution

Identifiers

Cite

Bernd Malle, Nicola Giuliani, Peter Kieseberg, Andreas Holzinger. The More the Merrier - Federated Learning from Local Sphere Recommendations. 1st International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2017, Reggio, Italy. pp.367-373, ⟨10.1007/978-3-319-66808-6_24⟩. ⟨hal-01677145⟩
215 View
205 Download

Altmetric

Share

Gmail Facebook X LinkedIn More