Graphnet: Graph Clustering with Deep Neural Networks

Zhang, Xianchao; Mu, Jie; Liu, Han

doi:10.1109/icassp39728.2021.9413809

Cited by 6 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Approaches towards generating graph embeddings include matrix factorization, deep learning with and without random walks, edge reconstruction, graph kernels, and generative models (Cai, Zheng, and Chang 2018). By either optimizing embeddings for their specific task or using general embedding techniques like node2vec, these graph embeddings may then be combined with existing techniques to tackle tasks such as node classification, node clustering, and link detection (Wang et al 2017) (Zhang et al 2021) (Crichton et al 2018 (Kipf and Welling 2016).…”

Section: Related Workmentioning

confidence: 99%

“…Other existing coordinate systems have also been used. Building off of network routing schemes in hyperbolic spaces, Rigel used a hyperbolic graph coordinate system to reduce the MRE to 9% and found that the hyperbolic space performed empirically better across distortion metrics than Euclidean and spherical coordinate systems (Cvetkovski and Crovella 2009;Zhao et al 2011). In road networks, geographical coordinates have been utilized with a multi-layer perceptron to predict distances between locations with 9% MRE (Jindal et al 2017).…”

Section: Related Workmentioning

confidence: 99%

“…However, in the real-world, the paths themselves are also often needed. Using the above methods to query for the shortest path length, routing algorithms can be constructed by performing a breadth-first search, where at each step only neighbors whose distance to the target is close to the current nodes' distance to the target are visited (Zhao et al 2011). Another framework finds the shortest path in the routing process, decomposing a large shortest path instance and solving it using reinforcement learning (Yin, Rao, and Zhang 2021).…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Deep Distance Sensitivity Oracles

Jeong¹,

Pham²,

Bhakta³

et al. 2022

Preprint

View full text Add to dashboard Cite

One of the most fundamental graph problems is finding a shortest path from a source to a target node. While in its basic forms the problem has been studied extensively and efficient algorithms are known, it becomes significantly harder as soon as parts of the graph are susceptible to failure. Although one can recompute a shortest replacement path after every outage, this is rather inefficient both in time and/or storage. One way to overcome this problem is to shift computational burden from the queries into a pre-processing step, where a data structure is computed that allows for fast querying of replacement paths, typically referred to as a Distance Sensitivity Oracle (DSO). Such a DSO can be constructed, by utilizing the fact that the shortest path in a graph with failures consists of a concatenation of shortest paths in the original graph. That is, one can quickly compute a replacement path by determining a suitable pivot and concatenating the shortest paths from source to pivot and from pivot to target. Unfortunately, finding such a pivot is far from trivial. In this paper, we utilize node2vec, graph attention networks, and multi-layer perceptrons to find pivots such that the lengths of the resulting paths are close to that of the shortest replacement paths. More precisely, we evaluate our technique on a collection of real-world networks and observe that on average the computed replacement paths are longer by merely a few percentages compared to the optimal solution. While DSOs have been extensively studied in the theoretical computer science community, to the best of our knowledge this is the first work to construct DSOs using deep learning techniques. In particular, in this work we first prove the existence of a combinatorial structure and then build on top of it a deep learning algorithm that utilizes the observed combinatorial structure. As mentioned above -we utilize the combinatorial structure of replacement paths as a concatenation of shortest paths and use deep learning to find the pivot nodes for stitching shortest paths into replacement paths.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep Distance Sensitivity Oracles

Jeong¹,

Pham²,

Bhakta³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Although, plenty of GNN-based algorithms have been presented to cope with various machine learning tasks, e.g., handwritten signature recognition [ 31 , 37 ], document discrimination [ 32 , 35 ], ranking [ 33 ], program verification [ 34 ], and human activity detection [ 38 ]. In recent 5 years, for instance, Zhang et al [ 39 ], proposed a deep graph clustering framework. First, a feature transformation module is built up of both the node and graph topology.…”

Section: Introductionmentioning

confidence: 99%

Virtual Reality and Internet of Things-Based Music Online Learning via the Graph Neural Network

Lian

Zhou

Han³

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Virtual reality and the Internet of Things have shown their capability in a variety of tasks. However, their availability in online learning remains an unresolved issue. To bridge this gap, we propose a virtual reality and Internet of Things-based pipeline for online music learning. The one graph network is used to generate an automated evaluation of learning performance which traditionally was given by the teachers. To be specific, a graph neural network-based algorithm is employed to identify the real-time status of each student within an online class. In the proposed algorithm, the characteristics of each student collected from the multisensors deployed on their bodies are taken as the input feature for each node in the presented graph neural network. With the adoption of convolutional layers and dense layers as well as the similarity between each pair of students, the proposed approach can predict the future circumstance of the entire class. To evaluate the performance of our work, comparison experiments between several state-of-the-art algorithms and the proposed algorithm were conducted. The result from the experiments demonstrated that the graph neural network-based algorithm achieved competitive performance (sensitivity 91.24%, specificity 93.58%, and accuracy 89.79%) over the state-of-the-art.

show abstract

Adaptive View-Aligned and Feature Augmentation Network for Partially View-Aligned Clustering

Zhang

Chen

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Graphnet: Graph Clustering with Deep Neural Networks

Cited by 6 publications

References 9 publications

Deep Distance Sensitivity Oracles

Deep Distance Sensitivity Oracles

Virtual Reality and Internet of Things-Based Music Online Learning via the Graph Neural Network

Adaptive View-Aligned and Feature Augmentation Network for Partially View-Aligned Clustering

Contact Info

Product

Resources

About