Diffusion network embedding

Shi, Yong; Lei, Minglong; Yang, Hong; Niu, Lingfeng

doi:10.1016/j.patcog.2018.12.004

Cited by 23 publications

(10 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2 shows the latent structures of the four datasets inferred from the information cascades by the diffusion sampling algorithm similar to the recent work in [Shi et al, 2019]. The information cascades are generated by simulating message propagation sequences sampled by multi-trace random walks, where time-interval sampling is used to generate the transmission time between nodes [Rodriguez et al, 2011].…”

Section: Methodsmentioning

confidence: 99%

Discrete Embedding for Latent Networks

Yang

Chen

Lei

et al. 2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Discrete network embedding emerged recently as a new direction of network representation learning. Compared with traditional network embedding models, discrete network embedding aims to compress model size and accelerate model inference by learning a set of short binary codes for network vertices. However, existing discrete network embedding methods usually assume that the network structures (e.g., edge weights) are readily available. In real-world scenarios such as social networks, sometimes it is impossible to collect explicit network structure information and it usually needs to be inferred from implicit data such as information cascades in the networks. To address this issue, we present an end-to-end discrete network embedding model for latent networks DELN that can learn binary representations from underlying information cascades. The essential idea is to infer a latent Weisfeiler-Lehman proximity matrix that captures node dependence based on information cascades and then to factorize the latent Weisfiler-Lehman matrix under the binary node representation constraint. Since the learning problem is a mixed integer optimization problem, an efficient maximal likelihood estimation based cyclic coordinate descent (MLE-CCD) algorithm is used as the solution. Experiments on real-world datasets show that the proposed model outperforms the state-of-the-art network embedding methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Discrete Embedding for Latent Networks

Yang

Chen

Lei

et al. 2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…By contrast, diffusion process considers the easiness of transitions between nodes in addition to the transition probabilities. For simplicity, we follow the general diffusion setting and denote the easiness of transition as the time passing from one node to another [15]. At the beginning, an initially activated root node is randomly selected from the node set V with time-stamp 0.…”

Section: Structure Learning Phasementioning

confidence: 99%

“…Specifically, there exist latent ties in networks that capture the uncertainty or possible node dependencies which have not been observed in current edges [14]. The latent ties can be described as the joint likelihood of transmission probabilities and transmission times [15]. For example, consider the epidemic spreading in a network, if an infectious source infects a node multi-hops away, there is supposed to have a latent tie between those two nodes and the strength between them describes the probability of infections and also how long it would take before the infection happens.…”

Section: Introductionmentioning

confidence: 99%

Latent Network Embedding via Adversarial Auto-encoders

Lei,

Shi,

Niu

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Graph auto-encoders have proved to be useful in network embedding task. However, current models only consider explicit structures and fail to explore the informative latent structures cohered in networks. To address this issue, we propose a latent network embedding model based on adversarial graph auto-encoders. Under this framework, the problem of discovering latent structures is formulated as inferring the latent ties from partial observations. A latent transmission matrix that describes the strengths of existing edges and latent ties is derived based on influence cascades sampled by simulating diffusion processes over networks. Besides, since the inference process may bring extra noises, we introduce an adversarial training that works as regularization to dislodge noises and improve the model robustness. Extensive experiments on link prediction and node classification tasks show that the proposed model achieves superior results compared with baseline models.

show abstract

“…Importantly, DL has the ability to learn more complex and heterogeneous representation for networks. The network diffusion based embeddings [86] methods can solve a number of limitations of the DL-based methods including heterogeneity, scalability, and multimodality.…”

Section: G Fusing Anomaly Detection and Social Influencementioning

confidence: 99%

Towards Deep Learning Prospects: Insights for Social Media Analytics

et al. 2019

View full text Add to dashboard Cite

Deep learning (DL) has attracted increasing attention on account of its significant processing power in tasks, such as speech, image, or text processing. In order to the exponential development and widespread availability of digital social media (SM), analyzing these data using traditional tools and technologies is tough or even intractable. DL is found as an appropriate solution to this problem. In this paper, we keenly discuss the practiced DL architectures by presenting a taxonomy-oriented summary, following the major efforts made toward the SM analytics (SMA). Nevertheless, instead of the technical description, this paper emphasis on describing the SMA-oriented problems with the DL-based solutions. To this end, we also highlight the DL research challenges (such as scalability, heterogeneity, and multimodality) and future trends. INDEX TERMS Social media data, dynamic network, deep learning, feature learning. I. INTRODUCTION

show abstract

Diffusion network embedding

Cited by 23 publications

References 39 publications

Discrete Embedding for Latent Networks

Discrete Embedding for Latent Networks

Latent Network Embedding via Adversarial Auto-encoders

Towards Deep Learning Prospects: Insights for Social Media Analytics

Contact Info

Product

Resources

About