paper-with-me

홈 › Papers

SUGAR: Efficient Subgraph-level Training via Resource-aware Graph Partitioning

2022-01-31 · Zihui Xue, Yuedong Yang, Mengtian Yang, Radu Marculescu

Graph Neural Networks (GNNs) have demonstrated a great potential in a variety of graph-based applications, such as recommender systems, drug discovery, and object recognition. Nevertheless, resource-efficient GNN learning is a rarely explored topic despite its many benefits for edge computing and Internet of Things (IoT) applications. To improve this state of affairs, this work proposes efficient subgraph-level training via resource-aware graph partitioning (SUGAR). SUGAR first partitions the initial graph into a set of disjoint subgraphs and then performs local training at the subgraph-level. We provide a theoretical analysis and conduct extensive experiments on five graph benchmarks to verify its efficacy in practice. Our results show that SUGAR can achieve up to 33 times runtime speedup and 3.8 times memory reduction on large-scale graphs. We believe SUGAR opens a new research direction towards developing GNN methods that are resource-efficient, hence suitable for IoT deployment.

📄 PDF Abstract BibTeX arXiv:2202.00075

Code (0)

등록된 구현이 없습니다.

Tasks

Drug DiscoveryEdge-computinggraph partitioningObject RecognitionRecommendation Systems

Similar Papers 제목 키워드 기반

SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism

2021-01-20 · Qingyun Sun, JianXin Li, Hao Peng, Jia Wu 외

Graph representation learning has attracted increasing research attention. However, most existing studies fuse all structural features and node attributes to provide an overarching view of graphs, neglecting finer substr…

Graph ClassificationGraph Neural NetworkGraph Representation LearningRepresentation Learning

Subgraph Aggregation for Out-of-Distribution Generalization on Graphs

2024-10-29 · Bowen Liu, Haoyang Li, Shuning Wang, Shuo Nie 외

Out-of-distribution (OOD) generalization in Graph Neural Networks (GNNs) has gained significant attention due to its critical importance in graph-based predictions in real-world scenarios. Existing methods primarily focu…

Molecular Property PredictionOut-of-Distribution GeneralizationProperty Prediction

SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases

2025-08-23 · Shifat E. Arman, Hasan Muhammad Abdullah, Syed Nazmus Sakib, RM Saiem 외 arxiv

Despite progress in AI-based plant diagnostics, sugarcane farmers in low-resource regions remain vulnerable to leaf diseases due to the lack of scalable, efficient, and interpretable tools. Many deep learning models fail…

Transfer Learning

PISA: Prioritized Invariant Subgraph Aggregation

2025-11-27 · Ali Ghasemi, Farooq Ahmad Wani, Maria Sofia Bucarelli, Fabrizio Silvestri arxiv

Recent work has extended the invariance principle for out-of-distribution (OOD) generalization from Euclidean to graph data, where challenges arise due to complex structures and diverse distribution shifts in node attrib…

SugarTextNet: A Transformer-Based Framework for Detecting Sugar Dating-Related Content on Social Media with Context-Aware Focal Loss

2025-11-09 · Lionel Z. Wang, Shihan Ben, Yulu Huang, Simeng Qin arxiv

Sugar dating-related content has rapidly proliferated on mainstream social media platforms, giving rise to serious societal and regulatory concerns, including commercialization of intimate relationships and the normaliza…