A United Approach to Learning Sparse Attributed Network Embedding

Wang, Hao; Chen, Enhong; Liu, Qi; Xu, Tong; Du, Dongfang; Su, Wen-Hao; Zhang, Xiaopeng

doi:10.1109/icdm.2018.00071

Cited by 44 publications

(16 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing Attributed Networks embedding methods can be categorized as: (a) random walk 41 based methods, (b) adjacency matrix decomposition-based methods, and (c) deep-learning-based methods. Among the random walk-based methods, SANE 42 learns the low dimensional representations by using random walk to generate node sequences and using attention mechanisms to aggregate the information of neighbor nodes. TADW 43 incorporates the DeepWalk and text features into an integrated framework for network representation learning.…”

Section: Attributed Network Embeddingmentioning

confidence: 99%

Deep Dual Support Vector Data description for anomaly detection on attributed networks

Zhang

Fan

Wang

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Networks are ubiquitous in the real world such as social networks and communication networks, and anomaly detection on networks aims at finding nodes whose structural or attributed patterns deviate significantly from the majority of reference nodes. However, most of the traditional anomaly detection methods neglect the relation structure information among data points and therefore cannot effectively generalize to the graph structure data. In this paper, we propose an end-to-end model of Deep Dual Support Vector Data description based Autoencoder (Dual-SVDAE) for anomaly detection on attributed networks, which considers both the structure and attribute for attributed networks. Specifically, Dual-SVDAE consists of a structure autoencoder and an attribute autoencoder to learn the latent representation of the node in the structure space and attribute space, respectively.Then, a dual-hypersphere learning mechanism is imposed on them to learn two hyperspheres of normal nodes from the structure and attribute perspectives, respectively. Moreover, to achieve joint learning between the structure and attribute of the network, we fuse the structure embedding and attribute embedding as the final input of the feature decoder to generate the node attribute. Finally, abnormal nodes can be

show abstract

Section: Attributed Network Embeddingmentioning

confidence: 99%

Deep Dual Support Vector Data description for anomaly detection on attributed networks

Zhang

Fan

Wang

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…In summary, the flowchart of MAAT framework is as Algorithm 1, which adpots a two-stage solution for the multiobjective optimization [34], [35]. MAAT has the following advantages: (1) it is model-agnostic and suitable for a wide range of CDMs, including those which traditional CAT methods cannot fit in; (2) it optimizes both quality and diversity with novel score functions and has an efficient performance-guaranteed optimization algorithm.…”

Section: F Summarymentioning

confidence: 99%

Quality meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing

Huang

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Computerized Adaptive Testing (CAT) is emerging as a promising testing application in many scenarios, such as education, game and recruitment, which targets at diagnosing the knowledge mastery levels of examinees on required concepts. It shows the advantage of tailoring a personalized testing procedure for each examinee, which selects questions step by step, depending on her performance. While there are many efforts on developing CAT systems, existing solutions generally follow an inflexible model-specific fashion. That is, they need to observe a specific cognitive model which can estimate examinee's knowledge levels and design the selection strategy according to the model estimation. In this paper, we study a novel model-agnostic CAT problem, where we aim to propose a flexible framework that can adapt to different cognitive models. Meanwhile, this work also figures out CAT solution with addressing the problem of how to generate both high-quality and diverse questions simultaneously, which can give a comprehensive knowledge diagnosis for each examinee. Inspired by Active Learning, we propose a novel framework, namely Model-Agnostic Adaptive Testing (MAAT) for CAT solution, where we design three sophisticated modules including Quality Module, Diversity Module and Importance Module. Specifically, at one CAT selection step, Quality Module first quantifies the informativeness of questions and generates candidate subset with the highest quality. Then, Diversity Module selects one question at each step that maximizes the concept coverage. Additionally, we propose Importance Module to estimate the importance of concepts that optimizes the CAT selection. Under MAAT, we prove that the goal of maximizing both quality and diversity is NP-hard, but we provide efficient algorithms by exploiting the inherent submodular property. Extensive experimental results on two real-world datasets clearly demonstrate that our MAAT can support CAT with guaranteeing both quality and diversity perspectives.

show abstract

“…Inspired by the remarkable development of graph neural networks in various domains [13] [40] [27] [39], researchers have noticed the potentials of them for molecular property prediction. Generally, by treating the molecule as a graph, several graph neural networks have been applied [14,24,40] as an architecture that can directly deal with noneuclidean data like graphs.…”

Section: Related Workmentioning

confidence: 99%

ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction

Hao

Huang

et al. 2020

Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

Self Cite

101

View full text Add to dashboard Cite

Molecular property prediction (e.g., energy) is an essential problem in chemistry and biology. Unfortunately, many supervised learning methods usually suffer from the problem of scarce labeled molecules in the chemical space, where such property labels are generally obtained by Density Functional Theory (DFT) calculation which is extremely computational costly. An effective solution is to incorporate the unlabeled molecules in a semi-supervised fashion. However, learning semi-supervised representation for large amounts of molecules is challenging, including the joint representation issue of both molecular essence and structure, the conflict between representation and property leaning. Here we propose a novel framework called Active Semi-supervised Graph Neural Network (ASGN) by incorporating both labeled and unlabeled molecules. Specifically, ASGN adopts a teacher-student framework. In the teacher model, we propose a novel semi-supervised learning method to learn general representation that jointly exploits information from molecular structure and molecular distribution. Then in the student model, we target at property prediction task to deal with the learning loss conflict. At last, we proposed a novel active learning strategy in terms of molecular diversities to select informative data during the whole framework learning. We conduct extensive experiments on several public datasets. Experimental results show the remarkable performance of our ASGN framework.

show abstract

A United Approach to Learning Sparse Attributed Network Embedding

Cited by 44 publications

References 23 publications

Deep Dual Support Vector Data description for anomaly detection on attributed networks

Deep Dual Support Vector Data description for anomaly detection on attributed networks

Quality meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing

ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction

Contact Info

Product

Resources

About