mlsanityData to 14 Oct 2026

GeoT: Tensor Centric Library for Graph Neural Network via Efficient Segment Reduction on GPU

arXiv 2404.03019 ↗First posted 3 Apr 2024cs.DC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In recent years, Graph Neural Networks (GNNs) have ignited a surge of innovation, significantly enhancing the processing of geometric data structures such as graphs, point clouds, and meshes. As the domain continues to evolve, a series of frameworks and libraries are being developed to push GNN efficiency to new heights. While graph-centric libraries have achieved success in the past, the advent of efficient tensor compilers has highlighted the urgent need for tensor-centric libraries. Yet, efficient tensor-centric frameworks for GNNs remain scarce due to unique challenges and limitations encountered when implementing segment reduction in GNN contexts. We introduce GeoT, a cutting-edge tensor-centric library designed specifically for GNNs via efficient segment reduction. GeoT debuts innovative parallel algorithms that not only introduce new design principles but also expand the available design space. Importantly, GeoT is engineered for straightforward fusion within a computation graph, ensuring compatibility with contemporary tensor-centric machine learning frameworks and compilers. Setting a new performance benchmark, GeoT marks a considerable advancement by showcasing an average operator speedup of 1.80x and an end-to-end speedup of 1.68x.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 88 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

44 of 88 references.

References · 44

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  10. 2019Simplifying Graph Convolutional Networkscited by 1,477
  11. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  12. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
32 more
  1. 2021E(n) Equivariant Graph Neural Networkscited by 965
  2. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  3. 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
  4. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  5. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
  6. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 267
  7. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 261
  8. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 259
  9. 2020Ansor: Generating High-Performance Tensor Programs for Deep Learningcited by 201
  10. 2019MLPerf Inference Benchmarkcited by 199
  11. 2020Sparse GPU Kernels for Deep Learningcited by 141
  12. 2018Learning to Optimize Tensor Programscited by 140
  13. 2017Predicting multicellular function through multi-layer tissue networkscited by 138
  14. 2020PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterestcited by 75
  15. 2021DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusioncited by 57
  16. 2020GNNAdvisor: An Adaptive and Efficient Runtime System for GNN Acceleration on GPUscited by 51
  17. 2022SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learningcited by 47
  18. 2020GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networkscited by 42
  19. 2022TensorIR: An Abstraction for Automatic Tensorized Program Optimizationcited by 38
  20. 2020Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilationcited by 29
  21. 2021Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspectivecited by 28
  22. 2022Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programscited by 28
  23. 2020FusedMM: A Unified SDDMM-SpMM Kernel for Graph Embedding and Graph Neural Networkscited by 26
  24. 2018Design Principles for Sparse Matrix Multiplication on the GPUcited by 19
  25. 2020Principled approach to the selection of the embedding dimension of networkscited by 19
  26. 2021The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Paddingcited by 17
  27. 2015Gunrock: A High-Performance Graph Processing Library on the GPUcited by 14
  28. 2023Relax: Composable Abstractions for End-to-End Dynamic Machine Learningcited by 12
  29. 2022Heuristic Adaptability to Input Dynamics for SpMM on GPUscited by 6
  30. 2022Sgap: Towards Efficient Sparse Tensor Algebra Compilation for GPUcited by 2
  31. 2023Hector: An Efficient Programming and Compilation Framework for Implementing Relational Graph Neural Networks in GPU Architecturescited by 1
  32. 2023Canvas: End-to-End Kernel Architecture Search in Neural Networkscited by 1

Built on by

Not cited yet.