方法对比

	图核	图神经网络	知识图谱嵌入
领域	网络分析	网络分析	网络分析
方法族	Machine learning	Process / pipeline	Machine learning
起源年份	2010	2017–2018 (major variants)	2013
提出者	Vishwanathan, Schraudolph, Kondor & Borgwardt	—	Bordes, Usunier, García-Durán, Weston & Yakhnenko
类型	Positive semi-definite kernel function over graphs	Deep learning on graph-structured data	Graph representation learning via low-dimensional vector embeddings
开创性文献	Vishwanathan, S. V. N., Schraudolph, N. N., Kondor, R., & Borgwardt, K. M. (2010). Graph kernels. Journal of Machine Learning Research, 11, 1201–1242.	Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR).	Bordes, A., Usunier, N., García-Durán, A., Weston, J., & Yakhnenko, O. (2013). Translating embeddings for modeling multi-relational data. Advances in Neural Information Processing Systems, 26.
别名	Structured Graph Kernels, Kernel Methods on Graphs, Graf Çekirdekleri, Graph Similarity Kernels	GNN, GCN, GAT, GraphSAGE	KG Embeddings, Knowledge Graph Representation Learning, Relational Embeddings, Bilgi Grafı Gömme
相关	2	5	3
摘要	Graph kernels are positive semi-definite kernel functions that measure the similarity between two graphs by comparing their shared substructures — such as random walks, shortest paths, or subtree patterns. Introduced in a unified framework by Vishwanathan, Schraudolph, Kondor, and Borgwardt (2010), they bridge kernel methods and graph-structured data, enabling algorithms like SVMs to operate directly on graphs without requiring an explicit vectorization step.	A Graph Neural Network (GNN) is a deep learning architecture that operates directly on graph-structured data by combining node features with structural information through iterative neighborhood message passing. The three canonical variants — the Graph Convolutional Network (GCN) introduced by Kipf and Welling in 2017, the Graph Attention Network (GAT) introduced by Veličković et al. in 2018, and GraphSAGE — differ in how they aggregate neighbor information: GCN applies a spectral convolution over the full adjacency, GAT weights neighbors by learned attention scores, and GraphSAGE samples and aggregates local neighborhoods inductively, enabling generalization to unseen nodes.	Knowledge Graph Embeddings (KGE) are a family of methods that represent entities and relations in a knowledge graph as dense, low-dimensional vectors in a continuous space. The foundational model, TransE, was introduced by Bordes, Usunier, García-Durán, Weston, and Yakhnenko in 2013. TransE treats each relation as a translation in embedding space — the head entity vector plus the relation vector should approximate the tail entity vector for any true triple (h, r, t). This simple geometric principle enabled effective link prediction and knowledge base completion at scale.