Task-Oriented Communication for Graph Data: A Graph Information Bottleneck Approach

TL;DR

This paper presents a graph information bottleneck approach using GNNs and vector quantization to efficiently transmit task-relevant subgraphs, reducing communication costs while maintaining essential information.

Contribution

It introduces a novel GIB-based method with VQ integration for task-oriented graph data transmission, addressing the complexity of graph structures.

Findings

Significantly reduces communication overhead.

Maintains high task performance with compressed graphs.

Robust across different communication channels.

Abstract

Graph data, essential in fields like knowledge representation and social networks, often involves large networks with many nodes and edges. Transmitting these graphs can be highly inefficient due to their size and redundancy for specific tasks. This paper introduces a method to extract a smaller, task-focused subgraph that maintains key information while reducing communication overhead. Our approach utilizes graph neural networks (GNNs) and the graph information bottleneck (GIB) principle to create a compact, informative, and robust graph representation suitable for transmission. The challenge lies in the irregular structure of graph data, making GIB optimization complex. We address this by deriving a tractable variational upper bound for the objective function. Additionally, we propose the VQ-GIB mechanism, integrating vector quantization (VQ) to convert subgraph representations into a discrete codebook sequence, compatible with existing digital communication systems. Our experiments show that this GIB-based method significantly lowers communication costs while preserving essential task-related information. The approach demonstrates robust performance across various communication channels, suitable for both continuous and discrete systems.