Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification
Graph Neural Architecture Search (GNAS) has achieved superior performance on various graph-structured tasks. However, existing GNAS studies overlook the applications of GNAS in resource-constraint scenarios. This paper proposes to design a joint graph data and architecture mechanism, which identifies important sub-architectures via the valuable graph data. To search for optimal lightweight Graph Neural Networks (GNNs), we propose a Lightweight Graph Neural Architecture Search with Graph SparsIfication and Network Pruning (GASSIP) method. In particular, GASSIP comprises an operation-pruned architecture search module to enable efficient lightweight GNN search. Meanwhile, we design a novel curriculum graph data sparsification module with an architecture-aware edge-removing difficulty measurement to help select optimal sub-architectures. With the aid of two differentiable masks, we iteratively optimize these two modules to efficiently search for the optimal lightweight architecture. Extensive experiments on five benchmarks demonstrate the effectiveness of GASSIP. Particularly, our method achieves on-par or even higher node classification performance with half or fewer model parameters of searched GNNs and a sparser graph.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Neural NetworkNetwork PruningNeural Architecture SearchNode ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines
As graphs scale to billions of nodes and edges, graph Machine Learning workloads are constrained by the cost of multi-hop traversals over exponentially growing neighborhoods. While various system-level and algorithmic op…
Graph Neural NetworkNode ClassificationFast Graph Attention Networks Using Effective Resistance Based Graph Sparsification
The attention mechanism has demonstrated superior performance for inference over nodes in graph neural networks (GNNs), however, they result in a high computational burden during both training and inference. We propose F…
Graph AttentionNode ClassificationA Unified Spectral Sparsification Framework for Directed Graphs
Recent spectral graph sparsification research allows constructing nearly-linear-sized subgraphs that can well preserve the spectral (structural) properties of the original graph, such as the first few eigenvalues and eig…
Enhancing Signed Graph Neural Networks through Curriculum-Based Training
Signed graphs are powerful models for representing complex relations with both positive and negative connections. Recently, Signed Graph Neural Networks (SGNNs) have emerged as potent tools for analyzing such graphs. To …
Link Sign PredictionRepresentation LearningA Generic Graph Sparsification Framework using Deep Reinforcement Learning
The interconnectedness and interdependence of modern graphs are growing ever more complex, causing enormous resources for processing, storage, communication, and decision-making of these graphs. In this work, we focus on…
Decision MakingDeep Reinforcement Learningreinforcement-learningReinforcement Learning+1