Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

hierarchical graph representation

A hierarchical graph representation is a multi-level structural model that organizes and encodes graph data across varying scales of granularity, ranging from fine-grained local elements to broader global configurations. Rather than treating a network as a single flat arrangement of individual nodes and edges, this approach systematically groups or pools interconnected components into higher-level abstract nodes, clusters, or subgraphs across progressive stages. By preserving both microscopic connectivity and macroscopic topological patterns, hierarchical graph representations enable analytical systems and neural architectures to efficiently capture multi-scale dependencies, community structures, and global topological properties.

1 item

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

Sixing Yu, Arya Mazaheri, Ali Jannesari

OrganizationsIowa State UniversityTechnische Universität Darmstadt

Why you should read this

Proposes a multi-stage graph embedding framework that captures hierarchical neural network topologies to automatically learn optimal, FLOP-constrained pruning policies via reinforcement learning across diverse architectures.

Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters’ local importance, ignoring the rich topology information within DNNs. In this paper, we propose a novel multi-stage graph embedding technique based on graph neural networks (GNNs) to identify DNN topologies and use reinforcement learning (RL) to find a suitable compression policy. We performed resource-constrained (i.e., FLOPs) channel pruning and compared our approach with state-of-the-art model compression methods. We evaluated our method on various models from typical to mobile-friendly networks, such as ResNet family, VGG-16, MobileNet-v1/v2, and ShuffleNet. Results show that our method can achieve higher compression ratios with a minimal fine-tuning cost yet yields outstanding and competitive performance. The code is open-sourced at https://github.com/yusx-swapp/GNN-RL-Model-Compression.

Added

2026-10-03