ExEm: Expert Embedding using dominating set theory with deep learning approaches

• URL: http://arxiv.org/abs/2001.08503v2
• Date: Fri, 22 Jan 2021 15:16:42 GMT
• Title: ExEm: Expert Embedding using dominating set theory with deep learning approaches
• Authors: N. Nikzad-Khasmakhi, M. A. Balafar, M.Reza Feizi-Derakhshi, Cina Motamed
• Abstract summary: We propose a graph embedding method, called ExEm, that uses dominating-set theory and deep learning approaches to capture node representations. ExEm exploits three embedding methods including Word2vec, fastText and the concatenation of these two. The extracted expert embeddings can be applied to many applications.
• Score: 2.131521514043068
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A collaborative network is a social network that is comprised of experts who cooperate with each other to fulfill a special goal. Analyzing this network yields meaningful information about the expertise of these experts and their subject areas. To perform the analysis, graph embedding techniques have emerged as an effective and promising tool. Graph embedding attempts to represent graph nodes as low-dimensional vectors. In this paper, we propose a graph embedding method, called ExEm, that uses dominating-set theory and deep learning approaches to capture node representations. ExEm finds dominating nodes of the collaborative network and constructs intelligent random walks that comprise of at least two dominating nodes. One dominating node should appear at the beginning of each path sampled to characterize the local neighborhoods. Moreover, the second dominating node reflects the global structure information. To learn the node embeddings, ExEm exploits three embedding methods including Word2vec, fastText and the concatenation of these two. The final result is the low-dimensional vectors of experts, called expert embeddings. The extracted expert embeddings can be applied to many applications. In order to extend these embeddings into the expert recommendation system, we introduce a novel strategy that uses expert vectors to calculate experts' scores and recommend experts. At the end, we conduct extensive experiments to validate the effectiveness of ExEm through assessing its performance over the multi-label classification, link prediction, and recommendation tasks on common datasets and our collected data formed by crawling the vast author Scopus profiles. The experiments show that ExEm outperforms the baselines especially in dense networks.

Related papers

• Exploring Unknown Social Networks for Discovering Hidden Nodes [0.0]
  We tackle the challenge of discovering hidden nodes in unknown social networks by employing a graph exploration framework grounded in machine learning. Our results show that our graph exploration strategies discover hidden nodes with an efficiency comparable to that when the graph structure is known.
  arXiv  Detail & Related papers  (2025-01-22T01:40:00Z)
• Knowledge Graph Pruning for Recommendation [44.21660467094777]
  We propose a novel approach called KGTrimmer for knowledge graph pruning tailored for recommendation. For the collective view, we embrace the idea of collective intelligence by extracting community consensus based on abundant collaborative signals. Next, we build an end-to-end importance-aware graph neural network, which injects filtered knowledge to enhance the distillation of valuable user-item collaborative signals.
  arXiv  Detail & Related papers  (2024-05-19T12:07:24Z)
• Mixture of Weak & Strong Experts on Graphs [56.878757632521555]
  Mixture of weak and strong experts (Mowst) Mowst is easy to optimize and achieves strong expressive power. On 4 backbone GNN architectures, Mowst shows significant accuracy improvement on 6 standard node classification benchmarks.
  arXiv  Detail & Related papers  (2023-11-09T07:45:05Z)
• Community Detection Guarantees Using Embeddings Learned by Node2Vec [5.530212768657544]
  We show that clustering on the embedding produced by node2vec gives weakly consistent community recovery for the nodes in block models. We also discuss the use of these embeddings for node and link prediction tasks.
  arXiv  Detail & Related papers  (2023-10-26T18:16:23Z)
• Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy [84.11508381847929]
  Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks. We propose M-SMoE, which leverages routing statistics to guide expert merging. Our MC-SMoE achieves up to 80% memory and a 20% FLOPs reduction, with virtually no loss in performance.
  arXiv  Detail & Related papers  (2023-10-02T16:51:32Z)
• STERLING: Synergistic Representation Learning on Bipartite Graphs [78.86064828220613]
  A fundamental challenge of bipartite graph representation learning is how to extract node embeddings. Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs. We introduce a novel synergistic representation learning model (STERLING) to learn node embeddings without negative node pairs.
  arXiv  Detail & Related papers  (2023-01-25T03:21:42Z)
• Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis [96.53859361560505]
  We propose a knowledge graph augmented network (KGAN) to incorporate external knowledge with explicitly syntactic and contextual information. KGAN captures the sentiment feature representations from multiple perspectives, i.e., context-, syntax- and knowledge-based. Experiments on three popular ABSA benchmarks demonstrate the effectiveness and robustness of our KGAN.
  arXiv  Detail & Related papers  (2022-01-13T08:25:53Z)
• Unveiling Anomalous Edges and Nominal Connectivity of Attributed Networks [53.56901624204265]
  The present work deals with uncovering anomalous edges in attributed graphs using two distinct formulations with complementary strengths. The first relies on decomposing the graph data matrix into low rank plus sparse components to improve markedly performance. The second broadens the scope of the first by performing robust recovery of the unperturbed graph, which enhances the anomaly identification performance.
  arXiv  Detail & Related papers  (2021-04-17T20:00:40Z)
• Evaluating Node Embeddings of Complex Networks [0.0]
  Agood embedding should capture the graph topology, node-to-node relationship, and other relevant information about the graph. The main challenge is that one needs to make sure that embeddings describe the properties of the graphs well. We do a series of experiments with selected graph embedding algorithms, both on real-world networks as well as artificially generated ones.
  arXiv  Detail & Related papers  (2021-02-16T16:55:29Z)
• Node2Seq: Towards Trainable Convolutions in Graph Neural Networks [59.378148590027735]
  We propose a graph network layer, known as Node2Seq, to learn node embeddings with explicitly trainable weights for different neighboring nodes. For a target node, our method sorts its neighboring nodes via attention mechanism and then employs 1D convolutional neural networks (CNNs) to enable explicit weights for information aggregation. In addition, we propose to incorporate non-local information for feature learning in an adaptive manner based on the attention scores.
  arXiv  Detail & Related papers  (2021-01-06T03:05:37Z)
• Adversarial Context Aware Network Embeddings for Textual Networks [8.680676599607123]
  Existing approaches learn embeddings of text and network structure by enforcing embeddings of connected nodes to be similar. This implies that these approaches require edge information for learning embeddings and they cannot learn embeddings of unseen nodes. We propose an approach that achieves both modality fusion and the capability to learn embeddings of unseen nodes.
  arXiv  Detail & Related papers  (2020-11-05T05:20:01Z)
• Integrating Network Embedding and Community Outlier Detection via Multiclass Graph Description [15.679313861083239]
  We propose a novel unsupervised graph embedding approach (called DMGD) which integrates outlier and community detection with node embedding. We show the theoretical bounds on the number of outliers detected by DMGD. Our formulation boils down to an interesting minimax game between the outliers, community assignments and the node embedding function.
  arXiv  Detail & Related papers  (2020-07-20T16:21:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.