Learning Large Graph Property Prediction via Graph Segment Training

• URL: http://arxiv.org/abs/2305.12322v3
• Date: Sun, 5 Nov 2023 18:27:55 GMT
• Title: Learning Large Graph Property Prediction via Graph Segment Training
• Authors: Kaidi Cao, Phitchaya Mangpo Phothilimthana, Sami Abu-El-Haija, Dustin Zelle, Yanqi Zhou, Charith Mendis, Jure Leskovec, Bryan Perozzi
• Abstract summary: We propose a general framework that allows learning large graph property prediction with a constant memory footprint. We refine the GST paradigm by introducing a historical embedding table to efficiently obtain embeddings for segments not sampled for backpropagation. Our experiments show that GST-EFD is both memory-efficient and fast, while offering a slight boost on test accuracy over a typical full graph training regime.
• Score: 61.344814074335304
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning to predict properties of large graphs is challenging because each prediction requires the knowledge of an entire graph, while the amount of memory available during training is bounded. Here we propose Graph Segment Training (GST), a general framework that utilizes a divide-and-conquer approach to allow learning large graph property prediction with a constant memory footprint. GST first divides a large graph into segments and then backpropagates through only a few segments sampled per training iteration. We refine the GST paradigm by introducing a historical embedding table to efficiently obtain embeddings for segments not sampled for backpropagation. To mitigate the staleness of historical embeddings, we design two novel techniques. First, we finetune the prediction head to fix the input distribution shift. Second, we introduce Stale Embedding Dropout to drop some stale embeddings during training to reduce bias. We evaluate our complete method GST-EFD (with all the techniques together) on two large graph property prediction benchmarks: MalNet and TpuGraphs. Our experiments show that GST-EFD is both memory-efficient and fast, while offering a slight boost on test accuracy over a typical full graph training regime.

Related papers

• Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness [80.87683145376305]
  Graph Neural Networks (GNNs) excel in various graph learning tasks but face computational challenges when applied to large-scale graphs. We propose Graph Sparse Training ( GST), which dynamically manipulates sparsity at the data level. GST produces a sparse graph with maximum topological integrity and no performance degradation.
  arXiv  Detail & Related papers  (2024-02-02T09:10:35Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Sparsity exploitation via discovering graphical models in multi-variate time-series forecasting [1.2762298148425795]
  We propose a decoupled training method, which includes a graph generating module and a GNNs forecasting module. First, we use Graphical Lasso (or GraphLASSO) to directly exploit the sparsity pattern from data to build graph structures. Second, we fit these graph structures and the input data into a Graph Convolutional Recurrent Network (GCRN) to train a forecasting model.
  arXiv  Detail & Related papers  (2023-06-29T16:48:00Z)
• Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphs [10.034072706245544]
  We propose a Time-aware Graph Structure Learning (TGSL) approach via sequence prediction on temporal graphs. In particular, it predicts time-aware context embedding and uses the Gumble-Top-K to select the closest candidate edges to this context embedding. Experiments on temporal link prediction benchmarks demonstrate that TGSL yields significant gains for the popular TGNs such as TGAT and GraphMixer.
  arXiv  Detail & Related papers  (2023-06-13T11:34:36Z)
• Scaling R-GCN Training with Graph Summarization [71.06855946732296]
  Training of Relation Graph Convolutional Networks (R-GCN) does not scale well with the size of the graph. In this work, we experiment with the use of graph summarization techniques to compress the graph. We obtain reasonable results on the AIFB, MUTAG and AM datasets.
  arXiv  Detail & Related papers  (2022-03-05T00:28:43Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)
• GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings [51.82434518719011]
  GNNAutoScale (GAS) is a framework for scaling arbitrary message-passing GNNs to large graphs. Gas prunes entire sub-trees of the computation graph by utilizing historical embeddings from prior training iterations. Gas reaches state-of-the-art performance on large-scale graphs.
  arXiv  Detail & Related papers  (2021-06-10T09:26:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.