A Comparison between Recursive Neural Networks and Graph Neural Networks

Abstract

Recursive neural networks (RNNs) and graph neural networks (GNNs) are two connectionist models that can directly process graphs. RNNs and GNNs exploit a similar processing framework, but they can be applied to different input domains. RNNs require the input graphs to be directed and acyclic, whereas GNNs can process any kind of graphs. The aim of this paper consists in understanding whether such a difference affects the behaviour of the models on a real application. An experimental comparison on an image classification problem is presented, showing that GNNs outperforms RNNs. Moreover the main differences between the models are also discussed w.r.t. their input domains, their approximation capabilities and their learning algorithms

Gated Graph Sequence Neural Networks

“…Micheli (2009) proposed another closely related model that differs from GNNs mainly in the output model. GNNs have been applied in several domains (Gori et al, 2005;Di Massa et al, 2006;Scarselli et al, 2009;Uwents et al, 2011), but they do not appear to be in widespread use in the ICLR community. Part of our aim here is to publicize GNNs as a useful and interesting neural network variant.…”

Graph neural network

“…分类 应用 节点分类 子图匹配、突变检测、网页排序 [10] 、团定位、二级蛋白质结构预测 [15] 网络垃圾邮件分类 [46] 、bAbI、规则发现 [16,18] 、文本挖掘 [47,48] 目标定位 [49] 、图像分类 [50] 、规则发现 [18] 、引文网络 [17,22] 、疾病预测 [51] Euclid 问题、文本分类 [21] 、知识图谱分类 [22] 、社团探测 [23] 、矩阵补全 [23,52] 组合优化 (TSP 问题、SAT 问题) [53][54][55][56] 、相近二进制码检测 [57] 、交通预测 [58] 链路预测 引文网络 [59,60] 、信息传播预测 [6] 、超图链路预测 [61] 图生成 小规模图生成 [62] 、化学分子图自动生成 [63] 社交网络、2D-网格图、蛋白质结构预测 [30] 、生成特定化学特性的分子 [28] 结构本身的拓扑信息, 影响最终的预测结果. 图神经网络则是直接处理图结构数据, 并且在迭代的过程 中始终利用了图本身的拓扑信息, 因此较之前的方法取得了更好的结果.…”

“…除此之外, 图神经网络还在其他的监督节点分类问题中被广泛地应用. 不仅给出了一些 NP-难 问题的近似算法, 如 TSP 问题 [55] 和 SAT 问题 [56] 等, 还在其他领域有许多重要的应用, 如文本挖 掘 [47,48] 、目标定位 [49] 、图像分类 [50] 、规则发现 [18] 、引文网络 [17] 和疾病预测 [51] 等. 这充分说明图神 经网络对于解决监督节点分类问题是一个行之有效的方法, 并且已经被广泛地应用在各个领域之中.…”

Addressing Cold Start in Recommender Systems with Hierarchical Graph Neural Networks

“…[24] first proposed Graph Neural Networks (GNN). Since then, the community has presented many variants for GNN, [25], [26]. These variants differ by graph types, training methods, and propagation step, [27].…”