.png){kind=icon}
.png){kind=icon}
Return
Robust Multi-Agent Communication via Diffusion-Based Message Denoising
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3438803.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multi-agent communication allows agents to share local information or their own intention with other agents, thus enhancing the collaborative performance of the multi-agent system. Despite its significance, previous multi-agent communication methods typically assume agents communicate in a perfect, interference-free environment without any communication disturbance. However, in real-world scenarios, communication within multi-agent systems often faces environmental noise, and even in adversarial settings, agents may encounter communication attacks from adversaries. How to maintain the collaborative stability within the multi-agent system under communication attack remains crucial yet inadequately researched. In this paper, we build a robust communication mechanism, DM2 (diffusion model to denoise the disturbed messages), which utilizes the denoising process of diffusion models to recover the original communicated messages, thus preventing the influence of communication interference. Besides, to reduce the computational burden brought by diffusion models, we design a detection module to recognize when the messages have been distorted, thus adopting the diffusion model only when necessary. The experiments show that, with this diffusion-based message denoising mechanism, our approach shows significantly superior communication robustness than existing baselines. Our approach exhibits excellent communication robustness in the presence of various types and different degrees of noise attacks. Visualization experiments and ablation studies validate the effectiveness of our diffusion model in recovering the original messages.
Keywords:
Diffusion models
Training
Noise reduction
Robustness
Reinforcement learning
Perturbation methods
Multi-agent systems
Multi-agent reinforcement learning
multi-agent communication
communication robustness
diffusion model
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W
Organization
No organization information available