PathSim
By Yizhou Sun, Jiawei Han, Xifeng Yan, Philip S. Yu, Tianyi Wu. Proceedings of the VLDB Endowment, 2011
1,600 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Signal Processing
View Paper: https://www.semanticscholar.org/paper/e7af1047d643ca833a7561dea750ead7a336ff27
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Statistical and Nonlinear Physics
In Signal Processing
Citations in the corpus
- A Survey on Knowledge Graph-Based Recommender Systems (2020, methodology): “The item-item similarity in each path is measured with PathSim [107], which further forms L item-item similar matrices S ( l ) ∈ R n × n , where l = 1 , 2 , · · · , L .”
- A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources (2020, neutral): “Meta-path [34].”
- OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs (2021, background): “Homophily is normally analyzed over a homogeneous graph, but we extend the analysis to the heterogenous graph by considering meta-paths (Sun et al., 2011)—a path consisting of a sequence of relations defined between different node types.”
- Heterogeneous Graph Neural Network (2019, background): “Heterogeneous graphs (HetG) [26, 27] contain abundant information with structural relations (edges) among multi-typed nodes as well as unstructured content associated with each node.”
- Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities (2018, background): “or each node (protein) in the network, such that the score reflects the probability that the protein is targeted by a particular drug [262,266,267]. In addition to random walks, one can use meta-paths [268] to extract drug and protein feature vectors from a heterogeneous network and thenfeedthem into”
- Heterogeneous Graph Transformer (2020, background): “One of the classical paradigms is to define and use meta paths to model heterogeneous structures, such as PathSim [18] and metapath2vec [3].”
- Semantic Proximity Search on Heterogeneous Graph by Proximity Embedding (2017, methodology): “In this paper, we study an important task, semantic proximity search on the graph (Sun et al. 2011; Fang et al. 2016b).”
- ClusCite: effective citation recommendation by information network-based clustering (2014, methodology): “We adopt the concept of network schema to describe the heterogeneous bibliographic network at the meta level [22, 23].”
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction (2021, methodology): “SimRank [28] uses advanced metrics such as the expected meeting distance on homogeneous graphs, which is extended by PathSim [51] to heterogeneous graphs.”
- Personalized entity recommendation: a heterogeneous information network approach (2014, methodology): “Studies regarding entity similarity measurements, as a fundamental technique, have been actively engaged in many research works as well [4] [11] [24].”
- Mining heterogeneous information networks: a structural analysis approach (2013, background): “Based on our research into mining heterogeneous information networks, especially our studies on ranking-based clustering [19; 22], ranking-based classification [10; 9], meta-path-based similarity search [18], relationship prediction [15; 16], and relation strength learning [14; 20], we believe there”
- Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec (2017, background): “For example, DeepWalk [28] and node2vec [15] define vertices’ context by the 1st and 2nd-order random walks, respectively; LINE defines a vertex’s context by its neighbors; Metapath2vec [11] defines vertex’s context by meta path [33].”