大规模图训练论文合集

Large-scale Training：研究大规模图训练，如经典的GraphSAGE和PinSAGE中做大规模邻居结点采样的方法。补充一点，这类研究实际上在各类框架上也有，例如DGL，PyG，Euler等。一方面可以进行训练方式改进，如邻居结点采样/子图采样等；另一方面也可以进行训练环境的分布式改造，分布式环境下，原始大图切割为子图分布在不同的机器中，如何进行子图间的通信、跨图卷积等，也是很有挑战的难点。
小编整理了近来的大规模图训练相关论文推荐给大家：
1.论文名称：Inductive Representation Learning on Large Graphs.
链接：https://www.aminer.cn/pub/599c7988601a182cd2648a09
2.论文名称：FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling.
链接：https://www.aminer.cn/pub/5a9cb66717c44a376ffb8667
3.论文名称：Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks.
链接：https://www.aminer.cn/pub/5cf48a3eda56291d582a1174
4.论文名称：GraphSAINT: Graph Sampling Based Inductive Learning Method
链接：https://www.aminer.cn/pub/5e5e18a493d709897ce22b32
5.论文名称：GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings
链接：https://www.aminer.cn/pub/60bdde338585e32c38af510f
6.论文名称：Scaling Graph Neural Networks with Approximate PageRank
链接：https://www.aminer.cn/pub/5f02f17c91e011ee5e0258c8
7.论文名称：Stochastic Training of Graph Convolutional Networks with Variance Reduction.
链接： https://www.aminer.cn/pub/5c8d4bf34895d9cbc64e3332
8.论文名称：Adaptive Sampling Towards Fast Graph Representation Learning.
链接：https://www.aminer.cn/pub/5bdc31b817c44a1f58a0c039
9.论文名称：SIGN: Scalable Inception Graph Neural Networks
链接：https://www.aminer.cn/pub/5ea2b8bf91e01167f5a89d89
10.论文名称：Simplifying Graph Convolutional Networks.
链接：https://www.aminer.cn/pub/5cede109da562983788e9c8b
11.论文名称：GraphSAINT: Graph Sampling Based Inductive Learning Method
链接：https://www.aminer.cn/pub/5e5e18a493d709897ce22b32
12.论文名称：GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings
链接：https://www.aminer.cn/pub/60bdde338585e32c38af510f
13.论文名称：Deep Graph Neural Networks with Shallow Subgraph Samplers
链接：https://www.aminer.cn/pub/5fc88628dfae549b1c499be1
14.论文名称：Scalable Graph Neural Networks via Bidirectional Propagation
链接：https://www.aminer.cn/pub/5f7fdd328de39f0828397afd
15.论文名称：A Unified Lottery Ticket Hypothesis for Graph Neural Networks
链接：https://www.aminer.cn/pub/602b8eb491e0113d72356b4f
16.论文名称：Scaling Graph Neural Networks with Approximate PageRank
链接：https://www.aminer.cn/pub/5f02f17c91e011ee5e0258c8
17.论文名称：Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
链接：https://www.aminer.cn/pub/60801e3391e011772654f9bf
18.论文名称：Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks.
链接：https://www.aminer.cn/pub/5cf48a3eda56291d582a1174
19.论文名称：GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding
链接：https://www.aminer.cn/pub/5e5e18b393d709897ce28ad3
20.论文名称：Global Neighbor Sampling for Mixed CPU-GPU Training on Giant Graphs.
链接：https://www.aminer.cn/pub/60c7fea791e0110a2be238c4
更多优质论文，尽在AMiner，主页添加关键词，系统智能推荐最新优质论文~
AMiner平台链接：
https://www.aminer.cn/?f=cs