mlsanityData to 7 Oct 2026

COIN: Communication-Aware In-Memory Acceleration for Graph Convolutional Networks

arXiv 2205.07311 ↗First posted 15 May 2022cs.AR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph convolutional networks (GCNs) have shown remarkable learning capabilities when processing graph-structured data found inherently in many application areas. GCNs distribute the outputs of neural networks embedded in each vertex over multiple iterations to take advantage of the relations captured by the underlying graphs. Consequently, they incur a significant amount of computation and irregular communication overheads, which call for GCN-specific hardware accelerators. To this end, this paper presents a communication-aware in-memory computing architecture (COIN) for GCN hardware acceleration. Besides accelerating the computation using custom compute elements (CE) and in-memory computing, COIN aims at minimizing the intra- and inter-CE communication in GCN operations to optimize the performance and energy efficiency. Experimental evaluations with widely used datasets show up to 105x improvement in energy consumption compared to state-of-the-art GCN accelerator.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 50 references that are in the map. First posted on arXiv 15 May 2022.

Builds on

19 of 50 references.

References · 19

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  4. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  5. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  6. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 241
  7. 2018Learning Scheduling Algorithms for Data Processing Clusterscited by 133
  8. 2019PyTorch-BigGraph: A Large-scale Graph Embedding Systemcited by 118
  9. 2020Computing Graph Neural Networks: A Survey from Algorithms to Acceleratorscited by 81
  10. 2020HyGCN: A GCN Accelerator with Hybrid Architecturecited by 73
  11. 2019EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networkscited by 42
  12. 2020GRIP: A Graph Neural Network Accelerator Architecturecited by 37
7 more
  1. 2021DeepScaleTool : A Tool for the Accurate Estimation of Technology Scaling in the Deep-Submicron Eracited by 27
  2. 2017GraphR: Accelerating Graph Processing Using ReRAMcited by 19
  3. 2020Rubik: A Hierarchical Architecture for Efficient Graph Learningcited by 7
  4. 2021SIAM: Chiplet-based Scalable In-Memory Acceleration with Mesh for Deep Neural Networkscited by 6
  5. 2021ReGraphX: NoC-enabled 3D Heterogeneous ReRAM Architecture for Training Graph Neural Networkscited by 5
  6. 2021Impact of On-Chip Interconnect on In-Memory Acceleration of Deep Neural Networkscited by 3
  7. 2015A Framework for General Sparse Matrix-Matrix Multiplication on GPUs and Heterogeneous Processorscited by 2

Built on by

Not cited yet.