Meta-Graph Based HIN Spectral Embedding: Methods, Analyses, and Insights

  title={Meta-Graph Based HIN Spectral Embedding: Methods, Analyses, and Insights},
  author={Carl Yang and Yichen Feng and Pan Li and Yu Shi and Jiawei Han},
  journal={2018 IEEE International Conference on Data Mining (ICDM)},
Heterogeneous information network (HIN) has drawn significant research attention recently, due to its power of modeling multi-typed multi-relational data and facilitating various downstream applications. [] Key Method Further, we explore the challenges of combining multiple meta-graphs to capture the multi-dimensional semantics in HIN through reasoning from mathematical geometry and arrive at an embedding compression method of autoencoder with l2,1-loss, which finds the most informative meta-graphs and…

Figures and Tables from this paper

mg2vec: Learning Relationship-Preserving Heterogeneous Graph Representations via Metagraph Embedding

This paper proposes the novel framework of mg2vec, which learns the embeddings for metagraphs and nodes jointly and significantly outperforms a suite of state-of-the-art baselines in relationship mining tasks including relationship prediction, search and visualization.

Heterogeneous Network Representation Learning: Survey, Benchmark, Evaluation, and Beyond

This work aims to provide a unified framework to deeply summarize and evaluate existing research on heterogeneous network embedding (HNE), and provides a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms.

Heterogeneous Network Representation Learning: A Unified Framework With Survey and Benchmark

This work aims to provide a unified framework to deeply summarize and evaluate existing research on heterogeneous network embedding (HNE), and provides a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms.

User-Guided Clustering in Heterogeneous Information Networks via Motif-Based Comprehensive Transcription

This work comprehensively transcribes the higher-order interaction signals to a series of tensors via motifs and proposes the MoCHIN model based on joint non-negative tensor factorization, which outperforms all baselines in three evaluation tasks under three different metrics.

Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks

Experimental results not only show HAEGNN’s superior performance against the state-of-the-art methods in node classification, node clustering, and visualization, but also demonstrate its superiorities in terms of memory efficiency and explainability.

Deep Generation of Heterogeneous Networks

This work proposes a novel framework for heterogeneous graph generation (HGEN) that jointly captures the semantic, structural, and global distributions of heterogeneous graphs and develops a novel heterogeneous walk generator that hierarchically generates meta-paths and their path instances.

DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks

Experimental results show that the proposed method can outperform state-of-the-art heterogeneous GNNs and also improves efficiency compared with those methods which can implicitly learn meta paths.

MultiSage: Empowering GCN with Contextualized Multi-Embeddings on Web-Scale Multipartite Networks

A contextualized GCN engine is presented by modeling the multipartite networks of target nodes and their intermediatecontext nodes that specify the contexts of their interactions to achieve interaction contextualization by treating neighboring target nodes based on intermediate context nodes.

CubeNet: Multi-Facet Hierarchical Heterogeneous Network Construction, Analysis, and Mining

This work outlines a novel framework called CubeNet, which systematically constructs and organizes real-world networks into different but correlated semantic cells, to support various downstream network analysis and mining tasks with better flexibility, deeper insights and higher efficiency.



Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks

This paper re-examine similarity search in HINs and proposes a novel embedding-based framework, ESim, that accepts user-defined meta-paths as guidance to learn vertex vectors in a user-preferred embedding space to explore network structure-embedded similarity.

Semi-supervised Learning over Heterogeneous Information Networks by Ensemble of Meta-graph Guided Random Walks

This paper decomposes the original HIN schema into several semantically meaningful meta-graphs consisting of entity and relation types and presents a semi-supervised learning algorithm constrained by the types of HINs.

Discovering Meta-Paths in Large Heterogeneous Information Networks

This work proposes a greedy algorithm to select the most relevant meta-paths and presents a data structure to enable efficient execution of this algorithm and incorporates hierarchical relationships among node classes in their solutions.

Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks

This paper introduces the concept of meta-graph to HIN-based recommendation, and solves the information fusion problem with a "matrix factorization + factorization machine (FM)" approach, and proposes to use FM with Group lasso (FMG) to automatically learn from the observed ratings to effectively select useful meta- graph based features.

metapath2vec: Scalable Representation Learning for Heterogeneous Networks

Two scalable representation learning models, namely metapath2vec and metapATH2vec++, are developed that are able to not only outperform state-of-the-art embedding models in various heterogeneous network mining tasks, but also discern the structural and semantic correlations between diverse network objects.

HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning

Empirical results show that HIN2Vec soundly outperforms the state-of-the-art representation learning models for network data, including DeepWalk, LINE, node2vec, PTE, HINE and ESim, by 6.6% to 23.8% of $micro$-$f_1$ in multi-label node classification and 5% to 70.8%, in link prediction.

PReP: Path-Based Relevance from a Probabilistic Perspective in Heterogeneous Information Networks

A generative model is established to derive a novel path-based relevance measure, which is data-driven and tailored for each HIN, and an inference algorithm is developed to find the maximum a posteriori (MAP) estimate of the model parameters, which entails non-trivial tricks.

AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks

This work proposes a novel embedding learning framework-ASPEM-to preserve the semantic information in HINs based on multiple aspects, where the aspects can be selected from the given HIN in an unsupervised manner.

A Local Algorithm for Structure-Preserving Graph Cut

This paper focuses on mining user-specified high-order network structures and proposes a novel High-Order Structure-Preserving LOcal Cut (HOSPLOC) algorithm, which runs in polylogarithmic time with respect to the number of edges in the graph.

LINE: Large-scale Information Network Embedding

A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures.