Graph Neural Networks: Architectures, Stability, and Transferability

Ruiz, Luana; Gama, Fernando; Ribeiro, Alejandro

doi:10.1109/jproc.2021.3055400

Cited by 96 publications

(46 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rather, classification is done based on the cost feature of each node in the graph which reflects how much estimation error is associated with the edges linked to each node. Furthermore, GNNs have the ability to perform estimations on graphs whose sizes are different from those in the training set, as analyzed in [41] and confirmed through the various tests conducted in this paper.…”

Section: Figure 4: Leave-set-out Cross-validation Results With Different Initial Random Seedssupporting

confidence: 64%

Pose-Graph Neural Network Classifier for Global Optimality Prediction in 2D SLAM

et al. 2021

View full text Add to dashboard Cite

The ability to decide if a solution to a pose-graph problem is globally optimal is of high significance for safety-critical applications. Converging to a local-minimum may result in severe estimation errors along the estimated trajectory. In this paper, we propose a graph neural network based on a novel implementation of a graph convolutional-like layer, called PoseConv, to perform classification of posegraphs as optimal or sub-optimal. The operation of PoseConv required incorporating a new node feature, referred to as cost, to hold the information that the nodes will communicate. A training and testing dataset was generated based on publicly available bench-marking pose-graphs. The neural classifier is then trained and extensively tested on several subsets of the pose-graph samples in the dataset. Testing results have proven the model's capability to perform classification with 92−98% accuracy, for the different partitions of the training and testing dataset. In addition, the model was able to generalize to previously unseen variants of pose-graphs in the training dataset. Our method trades a small amount of accuracy for a large improvement in processing time. This makes it faster than other existing methods by up-to three orders of magnitude, which could be of paramount importance when using computationally-limited robots overseen by human operators.

show abstract

Section: Figure 4: Leave-set-out Cross-validation Results With Different Initial Random Seedssupporting

confidence: 64%

Pose-Graph Neural Network Classifier for Global Optimality Prediction in 2D SLAM

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In addition, in table tennis, table tennis robot research has a very important position, and an excellent table tennis robot can help athletes improve their table tennis technology more efficiently [ 18 , 19 ]. This requires the table tennis robot to be able to locate the position of the table tennis ball in a short time, predict its trajectory in time, and select the appropriate and reasonable swing mode [ 20 – 23 ]. Therefore, the table tennis robot needs to accurately and automatically monitor the track of table tennis, that is, based on the position information of time series, it can predict the track of table tennis and the landing point on the table and can make the corresponding processing methods in real time [ 13 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

[Retracted] Automatic Detection Method of Technical and Tactical Indicators for Table Tennis Based on Trajectory Prediction Using Compensation Fuzzy Neural Network

Zhang

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In the system design of table tennis robot, the important influencing factors of automatic detection of technical and tactical indicators for table tennis are table tennis rotation state, trajectory, and rebound force. But the general prediction algorithm cannot process the time series data and give the corresponding rotation state. Therefore, this paper studies the automatic detection method of technical and tactical indicators for table tennis based on the trajectory prediction using the compensation fuzzy neural network. In this paper, the compensation fuzzy neural network algorithm which combines the compensation fuzzy algorithm and recurrent neural network is selected to construct the automatic detection of technical and tactical indicators for table tennis. The experimental results show that the convergence time of the compensation fuzzy neural network is shorter, the training time is shortened, and the prediction accuracy is improved. At the same time, in terms of performance testing, the model can accurately distinguish the influence of table tennis rotation state and rebound on table tennis motion estimation, so as to improve the accuracy of motion trajectory prediction. In addition, the accuracy of trajectory prediction will be improved with the increase of input data. When the number of data reaches 30, the trajectory prediction error is within the actual acceptable error range.

show abstract

“…Ruiz et al recently proposed a text classification method based on the principle of minimum description length, which can be applied to multilabel classification without transforming the classification problem. At the same time, it can make use of the dependent information between labels and naturally support online learning [ 1 ]. Höhn et al [ 2 ] designed a multilabel reasoning algorithm based on reasoning and adopted a new iterative reasoning mechanism to effectively use the information between labels, which can make use of the information between labels and avoid the problem of label order sensitivity.…”

Section: Introductionmentioning

confidence: 99%

[Retracted] Analysis of English Multitext Reading Comprehension Model Based on Deep Belief Neural Network

Tang

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In order to solve the problems of low accuracy and low efficiency of answer prediction in machine reading comprehension, a multitext English reading comprehension model based on the deep belief neural network is proposed. Firstly, the paragraph selector in the multitext reading comprehension model is constructed. Secondly, the text reader is designed, and the deep belief neural network is introduced to predict the question answering probability. Finally, the popular English dataset of SQuAD is used for test analysis. The final results show that, after the comparative analysis of different learning methods, it is found that the English multitext reading comprehension model has a strong reading comprehension ability. In addition, two evaluation methods are used to score the overall performance of the model, which shows that the overall score of the English multitext reading comprehension model based on the deep confidence neural network is more than 90, and the efficiency will not be reduced because of the change of the number of documents in the dataset. The above results show that the use of the deep belief neural network to improve the probability generation performance of the model can well solve the task of English multitext reading comprehension, effectively reduce the difficulty of machine reading comprehension in multitask reading, and has a good guiding significance for promoting human convenient Internet knowledge acquisition.

show abstract

Graph Neural Networks: Architectures, Stability, and Transferability

Cited by 96 publications

References 40 publications

Pose-Graph Neural Network Classifier for Global Optimality Prediction in 2D SLAM

Pose-Graph Neural Network Classifier for Global Optimality Prediction in 2D SLAM

[Retracted] Automatic Detection Method of Technical and Tactical Indicators for Table Tennis Based on Trajectory Prediction Using Compensation Fuzzy Neural Network

[Retracted] Analysis of English Multitext Reading Comprehension Model Based on Deep Belief Neural Network

Contact Info

Product

Resources

About