motif2vec: Motif Aware Node Representation Learning for Heterogeneous Networks

Dareddy, Manoj Reddy; Das, Mahashweta; Yang, Hao

doi:10.1109/bigdata47090.2019.9005670

Cited by 22 publications

(17 citation statements)

References 33 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This subsection reviews the generalized SkipGram-based graph embedding methods DeepWalk [56], Node2Vec [24], and Struc2Vec [58]; and the subgraph-based graph embedding methods DeepGK [73], Subgraph2Vec [48], RUM [75], Motif2Vec [15], and MotifWalk [50] . DeepWalk [56] was one of the earlist works to introduce the generalized SkipGram model to graph embedding.…”

Section: Generalized Skipgram-based Graph Embedding Methodsmentioning

confidence: 99%

“…Dareddy et al [15] propose another type of motif graph. Given a graph G = (V, E) , for each motif g, Motif2Vec builds a motif graph G � = (V, E � ) , where the weight of an edge (u, v) ∈ E � is the number of motif instances of g in G that contain node u and v. Then, Motif2Vec simulates a set of random walks on each motif graph and uses Node2Vec [24] to learn the embeddings of the nodes in G. A similar idea is also proposed in the MotifWalk method of [50].…”

Section: Generalized Skipgram-based Graph Embedding Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art

Peng

Choi

2021

Data Sci. Eng.

View full text Add to dashboard Cite

Graphs have been widely used to represent complex data in many applications, such as e-commerce, social networks, and bioinformatics. Efficient and effective analysis of graph data is important for graph-based applications. However, most graph analysis tasks are combinatorial optimization (CO) problems, which are NP-hard. Recent studies have focused a lot on the potential of using machine learning (ML) to solve graph-based CO problems. Most recent methods follow the two-stage framework. The first stage is graph representation learning, which embeds the graphs into low-dimension vectors. The second stage uses machine learning to solve the CO problems using the embeddings of the graphs learned in the first stage. The works for the first stage can be classified into two categories, graph embedding methods and end-to-end learning methods. For graph embedding methods, the learning of the the embeddings of the graphs has its own objective, which may not rely on the CO problems to be solved. The CO problems are solved by independent downstream tasks. For end-to-end learning methods, the learning of the embeddings of the graphs does not have its own objective and is an intermediate step of the learning procedure of solving the CO problems. The works for the second stage can also be classified into two categories, non-autoregressive methods and autoregressive methods. Non-autoregressive methods predict a solution for a CO problem in one shot. A non-autoregressive method predicts a matrix that denotes the probability of each node/edge being a part of a solution of the CO problem. The solution can be computed from the matrix using search heuristics such as beam search. Autoregressive methods iteratively extend a partial solution step by step. At each step, an autoregressive method predicts a node/edge conditioned to current partial solution, which is used to its extension. In this survey, we provide a thorough overview of recent studies of the graph learning-based CO methods. The survey ends with several remarks on future research directions.

show abstract

Section: Generalized Skipgram-based Graph Embedding Methodsmentioning

confidence: 99%

Section: Generalized Skipgram-based Graph Embedding Methodsmentioning

confidence: 99%

Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art

Peng

Choi

2021

Data Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…In comparison to GNNs, these methods usually only extract graph-level representations and not node-level. Motif-based node embeddings [66,67] and diffusion operators [68,69,70] that employ adjacency matrices weighted according to motif occurrences, have recently been proposed for graph representation learning; these can be expressed by our general formulation. Finally, GNNs that operate in larger induced neighbourhoods [71,72] or higher-order paths [73] have prohibitive complexity since the size of these neighbourhoods typically grows exponentially.…”

Section: Substructures In Complex Networkmentioning

confidence: 99%

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

Bouritsas¹,

Frasca²,

Zafeiriou³

et al. 2020

Preprint

View full text Add to dashboard Cite

While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of applications, recent studies exposed important shortcomings in their ability to capture the structure of the underlying graph. It has been shown that the expressive power of standard GNNs is bounded by the Weisfeiler-Lehman (WL) graph isomorphism test, from which they inherit proven limitations such as the inability to detect and count graph substructures. On the other hand, there is significant empirical evidence, e.g. in network science and bioinformatics, that substructures are often informative for downstream tasks, suggesting that it is desirable to design GNNs capable of leveraging this important source of information. To this end, we propose a novel topologically-aware message passing scheme based on subgraph isomorphism counting. We show that our architecture allows incorporating domain-specific inductive biases and that it is strictly more expressive than the WL test. Importantly, in contrast to recent works on the expressivity of GNNs, we do not attempt to adhere to the WL hierarchy; this allows us to retain multiple attractive properties of standard GNNs such as locality and linear complexity, while being able to disambiguate even hard instances of graph isomorphism. We extensively evaluate our method on graph classification and regression tasks and show state-of-the-art results on multiple datasets including molecular graphs and social networks.Preprint. Under review.

show abstract

“…On the contrary, MODEL is an individual algorithm and uses autoencoder to capture the nonlinear network structure. Motif2Vec [45] also leverages motifs, but its goal is to design a new random-walk method, which is unsatisfactory to capture the nonlinearity of the network structure. Furthermore, Motif2Vec focuses on heterogeneous networks, while MODEL focuses on homogeneous networks.…”

Section: Similar Workmentioning

confidence: 99%

MODEL: Motif-Based Deep Feature Learning for Link Prediction

Wang

Ren

et al. 2020

IEEE Trans. Comput. Soc. Syst.

View full text Add to dashboard Cite

Link prediction plays an important role in network analysis and applications. Recently, approaches for link prediction have evolved from traditional similarity-based algorithms into embedding-based algorithms. However, most existing approaches fail to exploit the fact that real-world networks are different from random networks. In particular, real-world networks are known to contain motifs, natural network building blocks reflecting the underlying network-generating processes. In this paper, we propose a novel embedding algorithm that incorporates network motifs to capture higher-order structures in the network. To evaluate its effectiveness for link prediction, experiments were conducted on three types of networks: social networks, biological networks, and academic networks. The results demonstrate that our algorithm outperforms both the traditional similarity-based algorithms (by 20%) and the stateof-the-art embedding-based algorithms (by 19%).

show abstract

motif2vec: Motif Aware Node Representation Learning for Heterogeneous Networks

Cited by 22 publications

References 33 publications

Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art

Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

MODEL: Motif-Based Deep Feature Learning for Link Prediction

Contact Info

Product

Resources

About