Hyper-Path-Based Representation Learning for Hyper-Networks

  title={Hyper-Path-Based Representation Learning for Hyper-Networks},
  author={Jie Huang and Xin Liu and Yangqiu Song},
  journal={Proceedings of the 28th ACM International Conference on Information and Knowledge Management},
  • Jie Huang, Xin Liu, Yangqiu Song
  • Published 24 August 2019
  • Computer Science
  • Proceedings of the 28th ACM International Conference on Information and Knowledge Management
Network representation learning has aroused widespread interests in recent years. While most of the existing methods deal with edges as pairwise relationships, only a few studies have been proposed for hyper-networks to capture more complicated tuplewise relationships among multiple nodes. A hyper-network is a network where each edge, called hyperedge, connects an arbitrary number of nodes. Different from conventional networks, hyper-networks have certain degrees of indecomposability such that… 

Figures and Tables from this paper

Representation Learning for Dynamic Hyperedges
A temporal point process model for hyperlink prediction that uses dynamic representation techniques for nodes to model the evolution and uses this representation in a neural point process framework to make inferences.
NHP: Neural Hypergraph Link Prediction
This paper proposes Neural Hyperlink Predictor (NHP), a deep learning-based approach for link prediction over directed hypergraphs that adapts Graph Convolutional Network (GCN) and proposes two variants of NHP --NHP-U and NHP-D -- for link Prediction over undirected and directedhypergraphs, respectively.
A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources
This survey presents several widely deployed systems that have demonstrated the success of HG embedding techniques in resolving real-world application problems with broader impacts and summarizes the open-source code, existing graph learning platforms and benchmark datasets.
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.
HYPER^2: Hyperbolic Poincare Embedding for Hyper-Relational Link Prediction
HYPER2 is proposed which is qualified for capturing the interaction between entities within and beyond triple through information aggregation on the tangent space, and generalize hyperbolic Poincaré embedding from binary to arbitrary arity data, which has not been studied yet.
Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
This work provides a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms, and creates four benchmark datasets with various properties regarding scale, structure, attribute/label availability, and \etc.~from different sources towards handy and fair evaluations of H NE algorithms.


Structural Deep Embedding for Hyper-Networks
It is theoretically prove that any linear similarity metric in embedding space commonly used in existing methods cannot maintain the indecomposibility property in hyper-networks, and thus a new deep model is proposed to realize a non-linear tuplewise similarity function while preserving both local and global proximities in the formedembedding space.
Hyper2vec: Biased Random Walk for Hyper-network Embedding
This paper proposes a deep model called Hyper2vec, which applies a biased \(2^{nd}\) order random walk strategy to hyper-networks in the framework of Skip-gram, which can be flexibly applied to various types of hyper- networks.
Modeling Multi-way Relations with Hypergraph Embedding
This paper designs an objective that is applicable to both uniform and non-uniform hypergraphs with the constraint of having non-negative embedding vectors, and applies negative sampling and constrained stochastic gradient descent to solve the optimization problem.
Heterogeneous Hyper-Network Embedding
A fully-connected and graph convolutional layers are designed to project different types of nodes into a common low-dimensional space, a tuple-wise similarity function is proposed to preserve the network structure, and a ranking based loss function is used to improve the similarity scores of hyperedges in the embedding space.
node2vec: Scalable Feature Learning for Networks
In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.
Learning with Hypergraphs: Clustering, Classification, and Embedding
This paper generalizes the powerful methodology of spectral clustering which originally operates on undirected graphs to hypergraphs, and further develop algorithms for hypergraph embedding and transductive classification on the basis of the spectral hypergraph clustering approach.
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.
BiNE: Bipartite Network Embedding
This work develops a representation learning method named BiNE, short for Bipartite Network Embedding, to learn the vertex representations for bipartite networks, and proposes a novel optimization framework by accounting for both the explicit and implicit relations in learning the vertices.
Deep Neural Networks for Learning Graph Representations
A novel model for learning graph representations, which generates a low-dimensional vector representation for each vertex by capturing the graph structural information directly, and which outperforms other stat-of-the-art models in such tasks.
Hypergraph spectral learning for multi-label classification
This paper proposes an approximate formulation of a hypergraph spectral learning formulation for multi-label classification, which is shown to be equivalent to a least squares problem under a mild condition and indicates that the approximate formulation is much more efficient than the original one, while keeping competitive classification performance.