arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.12192cs.LGstat.ML
收藏

GNN-FiLM:具有逐层线性调制的图神经网络

GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation

Microsoft Research(微软研究院)

Marc Brockschmidt

摘要:

本文提出了一种新的图神经网络(GNN)类型,使用特征线性调制(FiLM)。许多标准的GNN变体通过仅基于每条边的源的表示来计算“消息”来沿着图的边传播信息。在GNN-FiLM中,边缘的目标节点的表示还用于计算可应用于所有传入消息的变换,从而允许对传递的信息进行特征调制。实验结果比较不同的GNN架构上的三个任务,从文献中,重新实现的基线方法的基础上。使用广泛的搜索发现所有方法的超参数,产生了一些令人惊讶的结果:基线模型之间的差异小于文献中报道的差异。尽管如此,GNN-FiLM在分子图回归任务上的表现优于基线方法,并在其他任务上表现出竞争力。

英文摘要:

This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along the edges of a graph by computing "messages" based only on the representation of the source of each edge. In GNN-FiLM, the representation of the target node of an edge is additionally used to compute a transformation that can be applied to all incoming messages, allowing feature-wise modulation of the passed information. Results of experiments comparing different GNN architectures on three tasks from the literature are presented, based on re-implementations of baseline methods. Hyperparameters for all methods were found using extensive search, yielding somewhat surprising results: differences between baseline models are smaller than reported in the literature. Nonetheless, GNN-FiLM outperforms baseline methods on a regression task on molecular graphs and performs competitively on other tasks.

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。

↑