Collaborative Learning in General Graphs with Limited Memorization: Complexity, Learnability, and Reliability

• URL: http://arxiv.org/abs/2201.12482v3
• Date: Sun, 7 May 2023 01:32:59 GMT
• Title: Collaborative Learning in General Graphs with Limited Memorization: Complexity, Learnability, and Reliability
• Authors: Feng Li, Xuyang Yuan, Lina Wang, Huan Yang, Dongxiao Yu, Weifeng Lv, Xiuzhen Cheng
• Abstract summary: We consider a K-armed bandit problem in general graphs where agents are arbitrarily connected. The goal is to let each of the agents eventually learn the best arm. We propose a three-staged collaborative learning algorithm.
• Score: 30.432136485068572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider a K-armed bandit problem in general graphs where agents are arbitrarily connected and each of them has limited memorizing capabilities and communication bandwidth. The goal is to let each of the agents eventually learn the best arm. It is assumed in these studies that the communication graph should be complete or well-structured, whereas such an assumption is not always valid in practice. Furthermore, limited memorization and communication bandwidth also restrict the collaborations of the agents, since the agents memorize and communicate very few experiences. Additionally, an agent may be corrupted to share falsified experiences to its peers, while the resource limit in terms of memorization and communication may considerably restrict the reliability of the learning process. To address the above issues, we propose a three-staged collaborative learning algorithm. In each step, the agents share their latest experiences with each other through light-weight random walks in a general communication graph, and then make decisions on which arms to pull according to the recommendations received from their peers. The agents finally update their adoptions (i.e., preferences to the arms) based on the reward obtained by pulling the arms. Our theoretical analysis shows that, when there are a sufficient number of agents participating in the collaborative learning process, all the agents eventually learn the best arm with high probability, even with limited memorizing capabilities and light-weight communications. We also reveal in our theoretical analysis the upper bound on the number of corrupted agents our algorithm can tolerate. The efficacy of our proposed three-staged collaborative learning algorithm is finally verified by extensive experiments on both synthetic and real datasets.

Related papers

• Communication Learning in Multi-Agent Systems from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. We introduce a temporal gating mechanism for each agent, enabling dynamic decisions on whether to receive shared information at a given time.
  arXiv  Detail & Related papers  (2024-11-01T05:56:51Z)
• Learning Multi-Agent Communication from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. Our proposed approach, CommFormer, efficiently optimize the communication graph and concurrently refines architectural parameters through gradient descent in an end-to-end manner.
  arXiv  Detail & Related papers  (2024-05-14T12:40:25Z)
• Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning [57.652899266553035]
  Decentralized and lifelong-adaptive multi-agent collaborative learning aims to enhance collaboration among multiple agents without a central server. We propose DeLAMA, a decentralized multi-agent lifelong collaborative learning algorithm with dynamic collaboration graphs.
  arXiv  Detail & Related papers  (2024-03-11T09:21:11Z)
• Pure Exploration under Mediators' Feedback [63.56002444692792]
  Multi-armed bandits are a sequential-decision-making framework, where, at each interaction step, the learner selects an arm and observes a reward. We consider the scenario in which the learner has access to a set of mediators, each of which selects the arms on the agent's behalf according to a and possibly unknown policy. We propose a sequential decision-making strategy for discovering the best arm under the assumption that the mediators' policies are known to the learner.
  arXiv  Detail & Related papers  (2023-08-29T18:18:21Z)
• Building Cooperative Embodied Agents Modularly with Large Language Models [104.57849816689559]
  We address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various embodied environments. We harness the commonsense knowledge, reasoning ability, language comprehension, and text generation prowess of LLMs and seamlessly incorporate them into a cognitive-inspired modular framework. Our experiments on C-WAH and TDW-MAT demonstrate that CoELA driven by GPT-4 can surpass strong planning-based methods and exhibit emergent effective communication.
  arXiv  Detail & Related papers  (2023-07-05T17:59:27Z)
• On-Demand Communication for Asynchronous Multi-Agent Bandits [43.3383282058292]
  ODC is an on-demand communication protocol that tailors the communication of each pair of agents based on their empirical pull times. ODC is efficient when the pull times of agents are highly heterogeneous, and its communication complexity depends on the empirical pull times of agents.
  arXiv  Detail & Related papers  (2023-02-15T03:32:33Z)
• Communication-Efficient Collaborative Best Arm Identification [6.861971769602314]
  We investigate top-$m$ arm identification, a basic problem in bandit theory, in a multi-agent learning model in which agents collaborate to learn an objective function. We are interested in designing collaborative learning algorithms that achieve maximum speedup.
  arXiv  Detail & Related papers  (2022-08-18T19:02:29Z)
• Secure Distributed Training at Scale [65.7538150168154]
  Training in presence of peers requires specialized distributed training algorithms with Byzantine tolerance. We propose a novel protocol for secure (Byzantine-tolerant) decentralized training that emphasizes communication efficiency.
  arXiv  Detail & Related papers  (2021-06-21T17:00:42Z)
• A Visual Communication Map for Multi-Agent Deep Reinforcement Learning [7.003240657279981]
  Multi-agent learning poses significant challenges in the effort to allocate a concealed communication medium. Recent studies typically combine a specialized neural network with reinforcement learning to enable communication between agents. This paper proposes a more scalable approach that not only deals with a great number of agents but also enables collaboration between dissimilar functional agents.
  arXiv  Detail & Related papers  (2020-02-27T02:38:21Z)
• R-MADDPG for Partially Observable Environments and Limited Communication [42.771013165298186]
  This paper introduces a deep recurrent multiagent actor-critic framework (R-MADDPG) for handling multiagent coordination under partial observable set-tings and limited communication. We demonstrate that the resulting framework learns time dependencies for sharing missing observations, handling resource limitations, and developing different communication patterns among agents.
  arXiv  Detail & Related papers  (2020-02-16T21:25:44Z)
• Learning Multi-Agent Coordination through Connectivity-driven Communication [7.462336024223669]
  In artificial multi-agent systems, the ability to learn collaborative policies is predicated upon the agents' communication skills. We present a deep reinforcement learning approach, Connectivity Driven Communication (CDC) CDC is able to learn effective collaborative policies and can over-perform competing learning algorithms on cooperative navigation tasks.
  arXiv  Detail & Related papers  (2020-02-12T20:58:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.