Knowledge Sharing in AI Services: A Market-Based Approach
- 14 September 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (2) , 1320-1331
Abstract
Today’s deep neural networks (DNNs) are very accurate when trained on a large amount of data. However, suitable input might not be available or may require extensive data collection. Data sharing is one option to address these issues, but it is generally impractical because of privacy concerns or due to the problematic process of finding a sharing agreement. Instead, this work considers knowledge sharing by first exchanging the weights of pretrained DNNs and then applying transfer learning (TL). Specifically, it addresses the economics of knowledge sharing in AI services by taking a market-based approach. In detail, a model based on Fisher’s market is devised for optimal knowledge sharing, defined as the gain in inference accuracy from exchanging DNN weights. The proposed approach is shown to reach a market equilibrium and to satisfy important economic properties, including Pareto optimality. A technique for weight fusion is also introduced to merge acquired knowledge with the existing one. Finally, an extensive evaluation is conducted in a distributed intelligence scenario. The obtained results show that the proposed solution is efficient and that weight fusion with TL significantly increases inference accuracy compared to the original DNN, without the overhead of federated learning.Keywords
Funding Information
- Research Council of Finland (326346, 332307)
- European Commission through the Marie Skłodowska-Curie Actions COFUND REDI Project (101034328)
This publication has 31 references indexed in Scilit:
- A survey of deep neural network architectures and their applicationsNeurocomputing, 2017
- Learnware: on the future of machine learningFrontiers of Computer Science, 2016
- 3D Object Representations for Fine-Grained Categorization2013
- SPARSIProceedings of the VLDB Endowment, 2013
- Price Competition in an Oligopoly Market with Multiple IaaS Cloud ProvidersIEEE Transactions on Computers, 2013
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Market equilibrium via a primal--dual algorithm for a convex programJournal of the ACM, 2008
- Neuroanatomy: Cajal and after CajalBrain Research Reviews, 2007
- Algorithmic Game Theory2007
- Interior-point methodsJournal of Computational and Applied Mathematics, 2000