arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.00635cs.AI
收藏

Permutohedral-GCN:具有全局关注度的图卷积网络

Permutohedral-GCN: Graph Convolutional Networks with Global Attention

Artificial Intelligence Platforms Group, Intel Corporation(英特尔公司人工智能平台组)

Hesham Mostafa, Marcel Nassar

摘要:

图卷积网络(GCN)通过聚合图中节点邻居的特征来更新节点的特征向量。这忽略了来自远端节点的潜在有用贡献。由于可扩展性问题(太多的节点可能会做出贡献)和过度平滑(聚合来自太多节点的特征可能会淹没相关信息,并可能导致节点具有不同的标签但无法区分特征),识别这种有用的远程贡献是具有挑战性的。我们引入了一个全球性的注意力机制,其中一个节点可以有选择地参加,并聚合功能,在图中的任何其他节点。注意力系数取决于学习节点嵌入之间的欧氏距离,我们表明,由此产生的基于注意力的全球聚合计划类似于高维高斯滤波。这使得有可能使用有效的近似高斯滤波技术来实现我们的基于注意力的全球聚合计划。通过采用一种基于置换面体格的近似过滤方法,我们提出的全局聚集方案的时间复杂度仅随节点数线性增长。由此产生的GCN,我们称之为permutohedral-GCN,是可区分的,并且是端到端训练的,并且它们在几个节点分类基准上实现了最先进的性能。

英文摘要:

Graph convolutional networks (GCNs) update a node's feature vector by aggregating features from its neighbors in the graph. This ignores potentially useful contributions from distant nodes. Identifying such useful distant contributions is challenging due to scalability issues (too many nodes can potentially contribute) and oversmoothing (aggregating features from too many nodes risks swamping out relevant information and may result in nodes having different labels but indistinguishable features). We introduce a global attention mechanism where a node can selectively attend to, and aggregate features from, any other node in the graph. The attention coefficients depend on the Euclidean distance between learnable node embeddings, and we show that the resulting attention-based global aggregation scheme is analogous to high-dimensional Gaussian filtering. This makes it possible to use efficient approximate Gaussian filtering techniques to implement our attention-based global aggregation scheme. By employing an approximate filtering method based on the permutohedral lattice, the time complexity of our proposed global aggregation scheme only grows linearly with the number of nodes. The resulting GCNs, which we term permutohedral-GCNs, are differentiable and trained end-to-end, and they achieve state of the art performance on several node classification benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑