Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition

By Mohammad Rostami, Soheil Kolouri, Kyungnam Kim, Eric Eaton. 2017

39 citations recorded by the source corpus.

Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience. Current lifelong learning algorithms rely upon a single learning agent that has centralized access to all data. In this paper, we extend the idea of lifelong learning from a single agent to a network of multiple agents that collectively learn a series of tasks. Each agent faces some (potentially unique) set of tasks; the key idea is that knowledge learned from these tasks may benefit other agents trying to learn different (but related) tasks. Our Collective Lifelong Learning Algorithm (CoLLA) provides an efficient way for a network of agents to share their learned knowledge in a distributed and decentralized manner, while eliminating the need to share locally observed data. We provide theoretical guarantees for robust performance of the algorithm and empirically demonstrate that CoLLA outperforms existing approaches for distributed multi-task learning on a variety of datasets.

Subfields: Artificial Intelligence, Computer Networks and Communications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sung Ju Hwang
2. Jaehong Yoon
3. Eunho Yang
4. Giwoong Lee
5. Mohammad Rostami
6. Wonyoung Jeong
7. Abrar Rahman
8. Aswin Raghavan

In Computer Networks and Communications

1. Mohammad Rostami
2. Eunho Yang
3. Giwoong Lee
4. Sung Ju Hwang

Citations in the corpus

• Federated Continual Learning with Weighted Inter-client Transfer (2020, background): “CoLLA (21) aims at solving multi-agent lifelong learning with sparse dictionary learning, but it is not applicable to federated learning or continual deep learning.”
• Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2 (2022, background): “, 2021) and federated learning (Rostami et al., 2017), where communication between agents can enable better coordination between agents and collective acquisition of knowledge and to alleviate model obsolescence of machine learning-based (Sculley et al.”
• Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer (2017, unknown): “…(Ruvolo & Eaton, 2013), and later developed for policy gradient reinforcement learning (PG-ELLA) (Bou Ammar, Eaton, & Ruvolo, 2014) and collective multi-agent learning (Rostami, Kolouri, Kim, & Eaton, 2018) using distributed optimization (Hao, Oghbaee, Rostami, Derbinsky, & Bento, 2016).”
• Learning Transferable Knowledge Through Embedding Spaces (2019, background): “Results of this chapter have been presented in [228; 43; 229; 230].”