Distributed and Democratized Learning: Philosophy and Research Challenges

Due to the availability of huge amounts of data and processing abilities, current artificial intelligence (AI) systems are effective in solving complex tasks. However, despite the success of AI in different areas, the problem of designing AI systems that can truly mimic human cognitive capabilities such as artificial general intelligence, remains largely open. Consequently, many emerging cross-device AI applications will require a transition from traditional centralized learning systems towards large-scale distributed AI systems that can collaboratively perform multiple complex learning tasks. In this paper, we propose a novel design philosophy called democratized learning (Dem-AI) whose goal is to build large-scale distributed learning systems that rely on the self-organization of distributed learning agents that are wellconnected, but limited in learning capabilities. Correspondingly, inspired by the societal groups of humans, the specialized groups of learning agents in the proposed Dem-AI system are selforganized in a hierarchical structure to collectively perform learning tasks more efficiently. As such, the Dem-AI learning system can evolve and regulate itself based on the underlying duality of two processes which we call specialized and generalized processes. In this regard, we present a reference design as a guideline to realize future Dem-AI systems, inspired by various interdisciplinary fields. Accordingly, we introduce four underlying mechanisms in the design such as plasticity-stability transition mechanism, self-organizing hierarchical structuring, specialized learning, and generalization. Finally, we establish possible extensions and new challenges for the existing learning approaches to provide better scalable, flexible, and more powerful learning systems with the new setting of Dem-AI.

[1]  Zhu Han,et al.  Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanism , 2019, IEEE Communications Magazine.

[2]  Shuguang Cui,et al.  Convergence Time Minimization of Federated Learning over Wireless Networks , 2020, ICC 2020 - 2020 IEEE International Conference on Communications (ICC).

[3]  Eliseo Ferrante,et al.  Swarm robotics: a review from the swarm engineering perspective , 2013, Swarm Intelligence.

[4]  Zhu Han,et al.  Coalitional game theory for communication networks , 2009, IEEE Signal Processing Magazine.

[5]  Eui-Nam Huh,et al.  Self-organizing Democratized Learning: Towards Large-scale Distributed Learning Systems , 2020, ArXiv.

[6]  H. Vincent Poor,et al.  Experienced Deep Reinforcement Learning With Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communication , 2019, IEEE Transactions on Communications.

[7]  Yi Wu,et al.  Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments , 2017, NIPS.

[8]  Vipin Kumar,et al.  Chameleon: Hierarchical Clustering Using Dynamic Modeling , 1999, Computer.

[9]  Shimon Whiteson,et al.  Multi-Agent Common Knowledge Reinforcement Learning , 2018, NeurIPS.

[10]  Albert Y. Zomaya,et al.  Federated Learning over Wireless Networks: Optimization Model Design and Analysis , 2019, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications.

[11]  Stefan Wermter,et al.  Continual Lifelong Learning with Neural Networks: A Review , 2019, Neural Networks.

[12]  Stefan Wermter,et al.  Continual Lifelong Learning with Neural Networks: A Review , 2018, Neural Networks.

[13]  Choong Seon Hong,et al.  A Crowdsourcing Framework for On-Device Federated Learning , 2020, IEEE Transactions on Wireless Communications.

[14]  Walid Saad,et al.  Pricing in Heterogeneous Wireless Networks: Hierarchical Games and Dynamics , 2014, IEEE Transactions on Wireless Communications.

[15]  Fei Chen,et al.  Federated Meta-Learning with Fast Convergence and Efficient Communication , 2018 .

[16]  Xiaofei Wang,et al.  Federated Deep Reinforcement Learning for Internet of Things With Decentralized Cooperative Edge Caching , 2020, IEEE Internet of Things Journal.

[17]  Danielle S. Bassett,et al.  Network architectures supporting learnability , 2020, Philosophical Transactions of the Royal Society B.

[18]  Han Cha,et al.  Distilling On-Device Intelligence at the Network Edge , 2019, ArXiv.

[19]  Ameet Talwalkar,et al.  Federated Multi-Task Learning , 2017, NIPS.

[20]  D. Raulet,et al.  Immune surveillance of unhealthy cells by natural killer cells. , 2013, Cold Spring Harbor symposia on quantitative biology.

[21]  Bruno Sericola,et al.  MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets , 2018, 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS).

[22]  Yishay Mansour,et al.  Three Approaches for Personalization with Applications to Federated Learning , 2020, ArXiv.

[23]  Yu Zhang,et al.  A Survey on Multi-Task Learning , 2017, IEEE Transactions on Knowledge and Data Engineering.

[24]  Klaus-Robert Müller,et al.  Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[25]  Anit Kumar Sahu,et al.  Federated Optimization in Heterogeneous Networks , 2018, MLSys.

[26]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.

[27]  Aryan Mokhtari,et al.  Personalized Federated Learning: A Meta-Learning Approach , 2020, ArXiv.

[28]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[29]  I. Nonaka.  A Dynamic Theory of Organizational Knowledge Creation , 1994 .

[30]  -. LA-UR.  DIVERSITY IN DECENTRALIZED SYSTEMS : ENABLING SELF-ORGANIZING SOLUTIONS , 1999 .

[31]  Jiayu Zhou,et al.  Clustered Multi-Task Learning Via Alternating Structure Optimization , 2011, NIPS.

[32]  Walid Saad,et al.  A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks , 2021, IEEE Transactions on Wireless Communications.

[33]  Jean-Baptiste Mouret,et al.  The Evolutionary Origins of Hierarchy , 2015, PLoS Comput. Biol..

[34]  Ursula Challita,et al.  Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial , 2017, IEEE Communications Surveys & Tutorials.

[35]  Peter Dayan,et al.  Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning , 2019, ICLR 2019.

[36]  H. Vincent Poor,et al.  Convergence Time Optimization for Federated Learning Over Wireless Networks , 2020, IEEE Transactions on Wireless Communications.

[37]  Wojciech Samek,et al.  Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[38]  Chetan Nadiger,et al.  Federated Reinforcement Learning for Fast Personalization , 2019, 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE).

[39]  Xu Chen,et al.  In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning , 2018, IEEE Network.

[40]  Geoffrey E. Hinton,et al.  Similarity of Neural Network Representations Revisited , 2019, ICML.

[41]  Chin-Teng Lin,et al.  Reinforcement Learning From Hierarchical Critics , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[42]  Richard Nock,et al.  Advances and Open Problems in Federated Learning , 2019, Found. Trends Mach. Learn..

[43]  Joachim M. Buhmann,et al.  Variational Federated Multi-Task Learning , 2019, ArXiv.

[44]  Zhu Han,et al.  Game Theory for Next Generation Wireless and Communication Networks , 2019 .

[45]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[46]  Walid Saad,et al.  Brainstorming Generative Adversarial Networks (BGANs): Towards Multi-Agent Generative Models with Distributed Private Datasets , 2020, ArXiv.

[47]  Canh Dinh,et al.  Federated Learning Over Wireless Networks: Convergence Analysis and Resource Allocation , 2019, IEEE/ACM Transactions on Networking.

[48]  Pierre-Yves Oudeyer,et al.  Computational Theories of Curiosity-Driven Learning , 2018, ArXiv.

[49]  Jitendra Malik,et al.  Which Tasks Should Be Learned Together in Multi-task Learning? , 2019, ICML.