Unsupervised Heterophilous Network Embedding via $r$-Ego Network
Discrimination
- URL: http://arxiv.org/abs/2203.10866v1
- Date: Mon, 21 Mar 2022 10:40:44 GMT
- Title: Unsupervised Heterophilous Network Embedding via $r$-Ego Network
Discrimination
- Authors: Zhiqiang Zhong, Guadalupe Gonzalez, Daniele Grattarola, and Jun Pang
- Abstract summary: This paper introduces the first empirical study on the influence of homophily ratio on the performance of existing unsupervised NE methods.
We propose a dual-channel feature embedding mechanism to fuse node attributes and network structure information.
We conduct extensive experiments and a series of ablation studies on $12$ real-world and $20$ synthetic networks.
- Score: 7.220232621673462
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, supervised network embedding (NE) has emerged as a predominant
technique for representing complex systems that take the form of networks, and
various downstream node- and network-level tasks have benefited from its
remarkable developments. However, unsupervised NE still remains challenging due
to the uncertainty in defining a learning objective. In addition, it is still
an unexplored research question \textit{whether existing NE methods adapt well
to heterophilous networks}. This paper introduces the first empirical study on
the influence of homophily ratio on the performance of existing unsupervised NE
methods and reveals their limitations. Inspired by our empirical findings, we
design unsupervised NE task as an $r$-ego network discrimination problem and
further develop a \underline{SEL}f-sup\underline{E}rvised \underline{N}etwork
\underline{E}mbedding (Selene) framework for learning useful node
representations for both homophilous and heterophilous networks. Specifically,
we propose a dual-channel feature embedding mechanism to fuse node attributes
and network structure information and leverage a sampling and anonymisation
strategy to break the implicit homophily assumption of existing embedding
mechanisms. Lastly, we introduce a negative-sample-free SSL objective function
to optimise the framework. We conduct extensive experiments and a series of
ablation studies on $12$ real-world datasets and $20$ synthetic networks.
Results demonstrate Selene's superior performance and confirm the effectiveness
of each component. Code and data are available at
\url{https://github.com/zhiqiangzhongddu/Selene}.
Related papers
- Coding schemes in neural networks learning classification tasks [52.22978725954347]
We investigate fully-connected, wide neural networks learning classification tasks.
We show that the networks acquire strong, data-dependent features.
Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
arXiv Detail & Related papers (2024-06-24T14:50:05Z) - MAPPING: Debiasing Graph Neural Networks for Fair Node Classification
with Limited Sensitive Information Leakage [1.8238848494579714]
We propose a novel model-agnostic debiasing framework named MAPPING for fair node classification.
Our results show that MAPPING can achieve better trade-offs between utility and fairness, and privacy risks of sensitive information leakage.
arXiv Detail & Related papers (2024-01-23T14:59:46Z) - Interpolation-based Correlation Reduction Network for Semi-Supervised
Graph Learning [49.94816548023729]
We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN)
In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries.
By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
arXiv Detail & Related papers (2022-06-06T14:26:34Z) - Gradient Methods Provably Converge to Non-Robust Networks [40.83290846983707]
In adversarial networks, depth-$2LU$ Reperturbible gradient networks are provably non-robust.
We show that the well-known implicit bias towards a margin induces bias towards non-robust networks.
arXiv Detail & Related papers (2022-02-09T08:58:54Z) - Link Prediction with Contextualized Self-Supervision [63.25455976593081]
Link prediction aims to infer the existence of a link between two nodes in a network.
Traditional link prediction algorithms are hindered by three major challenges -- link sparsity, node attribute noise and network dynamics.
We propose a Contextualized Self-Supervised Learning framework that fully exploits structural context prediction for link prediction.
arXiv Detail & Related papers (2022-01-25T03:12:32Z) - Self-Ensembling GAN for Cross-Domain Semantic Segmentation [107.27377745720243]
This paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation.
In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN.
Despite its simplicity, we find SE-GAN can significantly boost the performance of adversarial training and enhance the stability of the model.
arXiv Detail & Related papers (2021-12-15T09:50:25Z) - Robustness Certificates for Implicit Neural Networks: A Mixed Monotone
Contractive Approach [60.67748036747221]
Implicit neural networks offer competitive performance and reduced memory consumption.
They can remain brittle with respect to input adversarial perturbations.
This paper proposes a theoretical and computational framework for robustness verification of implicit neural networks.
arXiv Detail & Related papers (2021-12-10T03:08:55Z) - SSSNET: Semi-Supervised Signed Network Clustering [4.895808607591299]
We introduce a novel probabilistic balanced normalized cut loss for training nodes in a GNN framework for semi-supervised signed network clustering, called SSSNET.
The main novelty approach is a new take on the role of social balance theory for signed network embeddings.
arXiv Detail & Related papers (2021-10-13T10:36:37Z) - Anomaly Detection on Attributed Networks via Contrastive Self-Supervised
Learning [50.24174211654775]
We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks.
Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair.
A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
arXiv Detail & Related papers (2021-02-27T03:17:20Z) - DINE: A Framework for Deep Incomplete Network Embedding [33.97952453310253]
We propose a Deep Incomplete Network Embedding method, namely DINE.
We first complete the missing part including both nodes and edges in a partially observable network by using the expectation-maximization framework.
We evaluate DINE over three networks on multi-label classification and link prediction tasks.
arXiv Detail & Related papers (2020-08-09T04:59:35Z)
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.