scholarly journals Topic Modeling on Document Networks with Adjacent-Encoder

2020 ◽  
Vol 34 (04) ◽  
pp. 6737-6745
Author(s):  
Ce Zhang ◽  
Hady W. Lauw
Keyword(s):  
Network Structure ◽  
Real World ◽  
Topic Modeling ◽  
Topic Model ◽  
Web Pages ◽  
Low Dimensional ◽  
Textual Content

Oftentimes documents are linked to one another in a network structure,e.g., academic papers cite other papers, Web pages link to other pages. In this paper we propose a holistic topic model to learn meaningful and unified low-dimensional representations for networked documents that seek to preserve both textual content and network structure. On the basis of reconstructing not only the input document but also its adjacent neighbors, we develop two neural encoder architectures. Adjacent-Encoder, or AdjEnc, induces competition among documents for topic propagation, and reconstruction among neighbors for semantic capture. Adjacent-Encoder-X, or AdjEnc-X, extends this to also encode the network structure in addition to document content. We evaluate our models on real-world document networks quantitatively and qualitatively, outperforming comparable baselines comprehensively.

scholarly journals Layer-Assisted Neural Topic Modeling over Document Networks

2021 ◽  
Author(s):  
Yiming Wang ◽  
Ximing Li ◽  
Jihong Ouyang
Keyword(s):  
Text Classification ◽  
Topic Modeling ◽  
Link Prediction ◽  
Topic Model ◽  
Web Pages ◽  
Text Documents ◽  
Text Data ◽  
Generative Process ◽  
Network Links ◽  
Scientific Papers

Neural topic modeling provides a flexible, efficient, and powerful way to extract topic representations from text documents. Unfortunately, most existing models cannot handle the text data with network links, such as web pages with hyperlinks and scientific papers with citations. To resolve this kind of data, we develop a novel neural topic model , namely Layer-Assisted Neural Topic Model (LANTM), which can be interpreted from the perspective of variational auto-encoders. Our major motivation is to enhance the topic representation encoding by not only using text contents, but also the assisted network links. Specifically, LANTM encodes the texts and network links to the topic representations by an augmented network with graph convolutional modules, and decodes them by maximizing the likelihood of the generative process. The neural variational inference is adopted for efficient inference. Experimental results validate that LANTM significantly outperforms the existing models on topic quality, text classification and link prediction..

scholarly journals Network Embedding with Dual Generation Tasks

2019 ◽  
Author(s):  
Jie Liu ◽  
Na Li ◽  
Zhicheng He
Keyword(s):  
Network Structure ◽  
Semantic Information ◽  
State Of The Art ◽  
Network Embedding ◽  
Intermediate Layers ◽  
Significant Performance ◽  
Low Dimensional ◽  
Textual Content ◽  
Core Problem ◽  
Dual Models

We study the problem of Network Embedding (NE) for content-rich networks. NE models aim to learn efficient low-dimensional dense vectors for network vertices which are crucial to many network analysis tasks. The core problem of content-rich network embedding is to learn and integrate the semantic information conveyed by network structure and node content. In this paper, we propose a general end-to-end model, Dual GEnerative Network Embedding (DGENE), to leverage the complementary information of network structure and content. In this model, each vertex is regarded as an object with two modalities: node identity and textual content. Then we formulate two dual generation tasks. One is Node Identification (NI) which recognizes nodes’ identities given their contents. Inversely, the other one is Content Generation (CG) which generates textual contents given the nodes’ identities. We develop specific Content2Node and Node2Content models for the two tasks. Under the DGENE framework, the two dual models are learned by sharing and integrating intermediate layers, with which they mutually enhance each other. Extensive experimental results show that our model yields a significant performance gain compared to the state-of-the-art NE methods. Moreover, our model has an interesting and useful byproduct, that is, a component of our model can generate texts, which is potentially useful for many tasks.

scholarly journals Principled approach to the selection of the embedding dimension of networks

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Weiwei Gu ◽  
Aditya Tandon ◽  
Yong-Yeol Ahn ◽  
Filippo Radicchi
Keyword(s):  
Real World ◽  
Structural Information ◽  
General Purpose ◽  
Embedding Dimension ◽  
Network Embedding ◽  
Machine Learning Technique ◽  
Learning Technique ◽  
Low Dimensional ◽  
Large Corpus ◽  
Selection Of

AbstractNetwork embedding is a general-purpose machine learning technique that encodes network structure in vector spaces with tunable dimension. Choosing an appropriate embedding dimension – small enough to be efficient and large enough to be effective – is challenging but necessary to generate embeddings applicable to a multitude of tasks. Existing strategies for the selection of the embedding dimension rely on performance maximization in downstream tasks. Here, we propose a principled method such that all structural information of a network is parsimoniously encoded. The method is validated on various embedding algorithms and a large corpus of real-world networks. The embedding dimension selected by our method in real-world networks suggest that efficient encoding in low-dimensional spaces is usually possible.

scholarly journals Predicting partially observed processes on temporal networks by Dynamics-Aware Node Embeddings (DyANE)

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Koya Sato ◽  
Mizuki Oka ◽  
Alain Barrat ◽  
Ciro Cattuto
Keyword(s):  
Network Structure ◽  
Machine Learning Algorithms ◽  
Temporal Networks ◽  
Dynamical Processes ◽  
Network Nodes ◽  
Partially Observed ◽  
Low Dimensional ◽  
Vector Representations ◽  
Infectious Disease Dynamics ◽  
Random Times

AbstractLow-dimensional vector representations of network nodes have proven successful to feed graph data to machine learning algorithms and to improve performance across diverse tasks. Most of the embedding techniques, however, have been developed with the goal of achieving dense, low-dimensional encoding of network structure and patterns. Here, we present a node embedding technique aimed at providing low-dimensional feature vectors that are informative of dynamical processes occurring over temporal networks – rather than of the network structure itself – with the goal of enabling prediction tasks related to the evolution and outcome of these processes. We achieve this by using a lossless modified supra-adjacency representation of temporal networks and building on standard embedding techniques for static graphs based on random walks. We show that the resulting embedding vectors are useful for prediction tasks related to paradigmatic dynamical processes, namely epidemic spreading over empirical temporal networks. In particular, we illustrate the performance of our approach for the prediction of nodes’ epidemic states in single instances of a spreading process. We show how framing this task as a supervised multi-label classification task on the embedding vectors allows us to estimate the temporal evolution of the entire system from a partial sampling of nodes at random times, with potential impact for nowcasting infectious disease dynamics.

A COMPETITIVE NEURAL NETWORK APPROACH TO WEB-PAGE CATEGORIZATION

2001 ◽  
Vol 09 (06) ◽  
pp. 731-741 ◽  
Author(s):  
ZHI-QIANG LIU ◽  
YA-JUN ZHANG
Keyword(s):  
Neural Network ◽  
Real World ◽  
Gradient Descent ◽  
Web Pages ◽  
Learning Method ◽  
Network Approach ◽  
Web Page ◽  
Real World Data ◽  
Neural Network Approach ◽  
Competitive Neural Network

Recently many techniques, e.g., Google or AltaVista, are available for classifying well-organized, hierarchical crisp categories from human constructed web pages such as that in Yahoo. However, given the current rate of web-page production, there is an urgent need of classifiers that are able to autonomously classify web-page categories that have overlaps. In this paper, we present a competitive learning method for this problem, which based on a new objective function and gradient descent scheme. Experimental results on real-world data show that the approach proposed in this paper gives a better performance in classifying randomly-generated, knowledge-overlapped categories as well as hierarchical crisp categories.

Extending Proximity Measures to Attributed Networks for Community Detection

2021 ◽  
Vol 30 (4) ◽  
pp. 441-455
Author(s):  
Rinat Aynulin ◽  
◽  
Pavel Chebotarev ◽  
◽  
Keyword(s):  
Network Analysis ◽  
Community Detection ◽  
Network Structure ◽  
Real World ◽  
Adjacency Matrix ◽  
Attribute Information ◽  
Node Attributes ◽  
Proximity Measures ◽  
Definition Of ◽  
Attributed Networks

Proximity measures on graphs are extensively used for solving various problems in network analysis, including community detection. Previous studies have considered proximity measures mainly for networks without attributes. However, attribute information, node attributes in particular, allows a more in-depth exploration of the network structure. This paper extends the definition of a number of proximity measures to the case of attributed networks. To take node attributes into account, attribute similarity is embedded into the adjacency matrix. Obtained attribute-aware proximity measures are numerically studied in the context of community detection in real-world networks.

Continual representation learning for evolving biomedical bipartite networks

2021 ◽  
Author(s):  
Kishlay Jha ◽  
Guangxu Xun ◽  
Aidong Zhang
Keyword(s):  
Network Structure ◽  
Learning Strategy ◽  
Structure Learning ◽  
Fundamental Problem ◽  
Representation Learning ◽  
Research Area ◽  
Bipartite Network ◽  
Bipartite Networks ◽  
Straightforward Application ◽  
Low Dimensional

Abstract Motivation Many real-world biomedical interactions such as ‘gene-disease’, ‘disease-symptom’ and ‘drug-target’ are modeled as a bipartite network structure. Learning meaningful representations for such networks is a fundamental problem in the research area of Network Representation Learning (NRL). NRL approaches aim to translate the network structure into low-dimensional vector representations that are useful to a variety of biomedical applications. Despite significant advances, the existing approaches still have certain limitations. First, a majority of these approaches do not model the unique topological properties of bipartite networks. Consequently, their straightforward application to the bipartite graphs yields unsatisfactory results. Second, the existing approaches typically learn representations from static networks. This is limiting for the biomedical bipartite networks that evolve at a rapid pace, and thus necessitate the development of approaches that can update the representations in an online fashion. Results In this research, we propose a novel representation learning approach that accurately preserves the intricate bipartite structure, and efficiently updates the node representations. Specifically, we design a customized autoencoder that captures the proximity relationship between nodes participating in the bipartite bicliques (2 × 2 sub-graph), while preserving both the global and local structures. Moreover, the proposed structure-preserving technique is carefully interleaved with the central tenets of continual machine learning to design an incremental learning strategy that updates the node representations in an online manner. Taken together, the proposed approach produces meaningful representations with high fidelity and computational efficiency. Extensive experiments conducted on several biomedical bipartite networks validate the effectiveness and rationality of the proposed approach.

scholarly journals Ego-zones: non-symmetric dependencies reveal network groups with large and dense overlaps

2019 ◽  
Vol 4 (1) ◽  
Author(s):  
Milos Kudelka ◽  
Eliska Ochodkova ◽  
Sarka Zehnalova ◽  
Jakub Plesnik
Keyword(s):  
Network Structure ◽  
Real World ◽  
Ground Truth ◽  
Structural Similarity ◽  
Global Network ◽  
Overlapping Communities ◽  
Detection Algorithms ◽  
First Case ◽  
New Perspective ◽  
The Individual

Abstract The existence of groups of nodes with common characteristics and the relationships between these groups are important factors influencing the structures of social, technological, biological, and other networks. Uncovering such groups and the relationships between them is, therefore, necessary for understanding these structures. Groups can either be found by detection algorithms based solely on structural analysis or identified on the basis of more in-depth knowledge of the processes taking place in networks. In the first case, these are mainly algorithms detecting non-overlapping communities or communities with small overlaps. The latter case is about identifying ground-truth communities, also on the basis of characteristics other than only network structure. Recent research into ground-truth communities shows that in real-world networks, there are nested communities or communities with large and dense overlaps which we are not yet able to detect satisfactorily only on the basis of structural network properties.In our approach, we present a new perspective on the problem of group detection using only the structural properties of networks. Its main contribution is pointing out the existence of large and dense overlaps of detected groups. We use the non-symmetric structural similarity between pairs of nodes, which we refer to as dependency, to detect groups that we call zones. Unlike other approaches, we are able, thanks to non-symmetry, accurately to describe the prominent nodes in the zones which are responsible for large zone overlaps and the reasons why overlaps occur. The individual zones that are detected provide new information associated in particular with the non-symmetric relationships within the group and the roles that individual nodes play in the zone. From the perspective of global network structure, because of the non-symmetric node-to-node relationships, we explore new properties of real-world networks that describe the differences between various types of networks.

scholarly journals Relation Structure-Aware Heterogeneous Information Network Embedding

2019 ◽  
Vol 33 ◽  
pp. 4456-4463 ◽  
Author(s):  
Yuanfu Lu ◽  
Chuan Shi ◽  
Linmei Hu ◽  
Zhiyuan Liu
Keyword(s):  
Real World ◽  
Dimensional Space ◽  
Structural Characteristics ◽  
Information Network ◽  
Network Embedding ◽  
Heterogeneous Information Network ◽  
Heterogeneous Information ◽  
Real World Datasets ◽  
Low Dimensional ◽  
Embedding Methods

Heterogeneous information network (HIN) embedding aims to embed multiple types of nodes into a low-dimensional space. Although most existing HIN embedding methods consider heterogeneous relations in HINs, they usually employ one single model for all relations without distinction, which inevitably restricts the capability of network embedding. In this paper, we take the structural characteristics of heterogeneous relations into consideration and propose a novel Relation structure-aware Heterogeneous Information Network Embedding model (RHINE). By exploring the real-world networks with thorough mathematical analysis, we present two structure-related measures which can consistently distinguish heterogeneous relations into two categories: Affiliation Relations (ARs) and Interaction Relations (IRs). To respect the distinctive characteristics of relations, in our RHINE, we propose different models specifically tailored to handle ARs and IRs, which can better capture the structures and semantics of the networks. At last, we combine and optimize these models in a unified and elegant manner. Extensive experiments on three real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods in various tasks, including node clustering, link prediction, and node classification.

scholarly journals Impact of road network structure on dementia-related missing incidents: a spatial buffer approach

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Vaisakh Puthusseryppady ◽  
Ed Manley ◽  
Ellen Lowry ◽  
Martyn Patel ◽  
Michael Hornberger
Keyword(s):  
Risk Factors ◽  
Network Structure ◽  
Environmental Risk ◽  
Real World ◽  
Road Network ◽  
Buffer Zone ◽  
Environmental Risk Factors ◽  
Life Threatening ◽  
Intersection Density ◽  
The Relationship

Abstract Dementia-related missing incidents are a highly prevalent issue worldwide. Despite being associated with potentially life-threatening consequences, very little is still known about what environmental risk factors may potentially contribute to these missing incidents. The aim of this study was to conduct a retrospective, observational analysis using a large sample of police case records of missing individuals with dementia (n = 210). Due to the influence that road network structure has on our real world navigation, we aimed to explore the relationship between road intersection density, intersection complexity, and orientation entropy to the dementia-related missing incidents. For each missing incident location, the above three variables were computed at a 1 km radius buffer zone around these locations; these values were then compared to that of a set of random locations. The results showed that higher road intersection density, intersection complexity, and orientation entropy were all significantly associated with dementia-related missing incidents. Our results suggest that these properties of road network structure emerge as significant environmental risk factors for dementia-related missing incidents, informing future prospective studies as well as safeguarding guidelines.

Sign in / Sign up

Export Citation Format

Share Document