arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.04652cs.LGstat.ML
收藏

基于硬注意网络和智能注意网络的图表示学习

Graph Representation Learning via Hard and Channel-Wise Attention Networks

Texas A&M University(德克萨斯农工大学)

Hongyang Gao, Shuiwang Ji

摘要:

注意力算子在计算机视觉、自然语言处理、网络嵌入学习等领域有着广泛的应用。图数据上的注意力操作符在聚合来自相邻节点的信息时启用可学习的权重。然而,图注意力算子(GAO)消耗过多的计算资源,阻碍了它们在大型图上的应用。此外,GAO属于软注意力家族,而不是硬注意力,这已被证明可以产生更好的性能。在这项工作中,我们提出了新的硬图注意力算子(hGAO)和通道式图注意力算子(cGAO)。hGAO通过仅关注重要节点来使用硬注意力机制。与GAO算法相比,hGAO算法只关注重要节点,提高了性能,节省了计算开销。为了进一步降低对计算资源的需求,我们提出了cGAO,它沿着通道执行注意力操作。cGAO避免了对邻接矩阵的依赖,从而大大减少了计算资源需求。实验结果表明,我们提出的深度模型与新的运营商实现了一贯更好的性能。比较结果还表明,hGAO在节点和图嵌入任务上的性能明显优于GAO。效率比较表明,我们的cGAO导致计算资源的显着节省,使其适用于大型图形。

英文摘要:

Attention operators have been widely applied in various fields, including computer vision, natural language processing, and network embedding learning. Attention operators on graph data enables learnable weights when aggregating information from neighboring nodes. However, graph attention operators (GAOs) consume excessive computational resources, preventing their applications on large graphs. In addition, GAOs belong to the family of soft attention, instead of hard attention, which has been shown to yield better performance. In this work, we propose novel hard graph attention operator (hGAO) and channel-wise graph attention operator (cGAO). hGAO uses the hard attention mechanism by attending to only important nodes. Compared to GAO, hGAO improves performance and saves computational cost by only attending to important nodes. To further reduce the requirements on computational resources, we propose the cGAO that performs attention operations along channels. cGAO avoids the dependency on the adjacency matrix, leading to dramatic reductions in computational resource requirements. Experimental results demonstrate that our proposed deep models with the new operators achieve consistently better performance. Comparison results also indicates that hGAO achieves significantly better performance than GAO on both node and graph embedding tasks. Efficiency comparison shows that our cGAO leads to dramatic savings in computational resources, making them applicable to large graphs.

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。

↑