Unifying Homophily and Heterophily Network Transformation via Motifs

• URL: http://arxiv.org/abs/2012.11400v2
• Date: Sun, 27 Dec 2020 15:36:46 GMT
• Title: Unifying Homophily and Heterophily Network Transformation via Motifs
• Authors: Yan Ge, Jun Ma, Li Zhang, Haiping Lu
• Abstract summary: Higher-order proximity (HOP) is fundamental for most network embedding methods. We propose homophily and heterophliy preserving network transformation (H2NT) to capture HOP that flexibly unifies homophily and heterophily. H2NT can be used as an enhancer to be integrated with any existing network embedding methods without requiring any changes to latter methods.
• Score: 20.45207959265955
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Higher-order proximity (HOP) is fundamental for most network embedding methods due to its significant effects on the quality of node embedding and performance on downstream network analysis tasks. Most existing HOP definitions are based on either homophily to place close and highly interconnected nodes tightly in embedding space or heterophily to place distant but structurally similar nodes together after embedding. In real-world networks, both can co-exist, and thus considering only one could limit the prediction performance and interpretability. However, there is no general and universal solution that takes both into consideration. In this paper, we propose such a simple yet powerful framework called homophily and heterophliy preserving network transformation (H2NT) to capture HOP that flexibly unifies homophily and heterophily. Specifically, H2NT utilises motif representations to transform a network into a new network with a hybrid assumption via micro-level and macro-level walk paths. H2NT can be used as an enhancer to be integrated with any existing network embedding methods without requiring any changes to latter methods. Because H2NT can sparsify networks with motif structures, it can also improve the computational efficiency of existing network embedding methods when integrated. We conduct experiments on node classification, structural role classification and motif prediction to show the superior prediction performance and computational efficiency over state-of-the-art methods. In particular, DeepWalk-based H2 NT achieves 24% improvement in terms of precision on motif prediction, while reducing 46% computational time compared to the original DeepWalk.

Related papers

• Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis [93.55896765176414]
  We propose binary sparse convolutional networks called BSC-Net for efficient point cloud analysis. We employ the differentiable search strategies to discover the optimal opsitions for active site matching in the shifted sparse convolution. Our BSC-Net achieves significant improvement upon our srtong baseline and outperforms the state-of-the-art network binarization methods.
  arXiv  Detail & Related papers  (2023-03-27T13:47:06Z)
• Binary Graph Convolutional Network with Capacity Exploration [58.99478502486377]
  We propose a Binary Graph Convolutional Network (Bi-GCN), which binarizes both the network parameters and input node attributes. Our Bi-GCN can reduce the memory consumption by an average of 31x for both the network parameters and input data, and accelerate the inference speed by an average of 51x.
  arXiv  Detail & Related papers  (2022-10-24T12:05:17Z)
• The Influence of Network Structural Preference on Node Classification and Link Prediction [0.0]
  This work introduces a new feature abstraction method, namely the Transition Probabilities Matrix (TPM) The success of the proposed embedding method is tested on node identification/classification and link prediction on three commonly used real-world networks.
  arXiv  Detail & Related papers  (2022-08-07T12:56:28Z)
• Propagation with Adaptive Mask then Training for Node Classification on Attributed Networks [10.732648536892377]
  node classification on attributed networks is a semi-supervised task that is crucial for network analysis. We propose a new method called the itshape propagation with Adaptive Mask then Training (PAMT) The key idea is to integrate the attribute similarity mask into the structure-aware propagation process. In this way, PAMT could preserve the correlation of the attribute of adjacent nodes during the propagation and effectively reduce the influence of structure noise.
  arXiv  Detail & Related papers  (2022-06-21T06:56:58Z)
• DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks [64.62314068155997]
  We present textitDecentralized Embedding Framework for Heterogeneous Information Network (DeHIN) in this paper. DeHIN presents a context preserving partition mechanism that innovatively formulates a large HIN as a hypergraph. Our framework then adopts a decentralized strategy to efficiently partition HINs by adopting a tree-like pipeline.
  arXiv  Detail & Related papers  (2022-01-08T04:08:36Z)
• Unsupervised Domain-adaptive Hash for Networks [81.49184987430333]
  Domain-adaptive hash learning has enjoyed considerable success in the computer vision community. We develop an unsupervised domain-adaptive hash learning method for networks, dubbed UDAH.
  arXiv  Detail & Related papers  (2021-08-20T12:09:38Z)
• Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs [28.77753005139331]
  We investigate the representation power of graph neural networks in a semi-supervised node classification task under heterophily or low homophily. Many popular GNNs fail to generalize to this setting, and are even outperformed by models that ignore the graph structure. We identify a set of key designs that boost learning from the graph structure under heterophily.
  arXiv  Detail & Related papers  (2020-06-20T02:05:01Z)
• Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
  This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-06T15:51:00Z)
• Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives [73.15276998621582]
  We propose a generic feature learning mechanism to advance CNN training with enhanced generalization ability. Partially inspired by DSN, we fork delicately designed side branches from the intermediate layers of a given neural network. Experiments on both category and instance recognition tasks demonstrate the substantial improvements of our proposed method.
  arXiv  Detail & Related papers  (2020-03-24T09:56:13Z)
• Adversarial Deep Network Embedding for Cross-network Node Classification [27.777464531860325]
  Cross-network node classification leverages the abundant labeled nodes from a source network to help classify unlabeled nodes in a target network. In this paper, we propose an adversarial cross-network deep network embedding model to integrate adversarial domain adaptation with deep network embedding. The proposed ACDNE model achieves the state-of-the-art performance in cross-network node classification.
  arXiv  Detail & Related papers  (2020-02-18T04:30:43Z)

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.