据我们所知,TactileSignet是第一个用于触觉数据的事件驱动图神经网络。一个相关的模型是最近提出的TactileGCN[16],它使用图卷积网络(GCN)[17]进行触觉对象识别。这项工作的关键区别在于,TactileSignet是事件驱动的(带有尖峰神经元),我们利用了拓扑自适应图卷积网络(TAGCN)[18];此前已证明,TAGCN具有优异的性能,同时...
Finally, the data were expanded into the time domain using a spiking neural network to train the model and propagate it backwards. This framework effectively utilizes the structural differences between sample instances in the spatial dimension to improve the representational power of spiking neurons, ...
Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed Slack-Free Spiking Neural Network Formulation for Hypergraph Minimum Vertex Cover DeepITE: Designing Variational Graph Autoencoders for Intervention Target Estimation LLMs as Zero-shot Graph Learners: Alignment of GNN Represetantions with LLM ...
1999. Solving graph algorithms with networks of spiking neurons. IEEE Transactions on Neural Networks, 10(4):953-957Doral M Sala,Krzysztof J Cios.Solving Graph Algorithms with Networks of Spiking Neurons. IEEE Transactions on Neural Networks . 1999...
Gong P, Wang P, Zhou Y, Zhang D (2023) A spiking neural network with adaptive graph convolution and lstm for eeg-based brain-computer interfaces. IEEE T Neur Sys Reh 31:1440–1450. https://doi.org/10.1109/TNSRE.2023.3246989 Article Google Scholar Bi J, Wang F, Yan X, Ping J, Wen...
Spiking neurons with spatiotemporal dynamics and gain modulation for monolithically integrated memristive neural networks. Nat. Commun. 11, 3399 (2020). Article Google Scholar Joshi, V. et al. Accurate deep neural network inference using computational phase-change memory. Nat. Commun. 11, 2473 (...
A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks They propose a novel spiking graph contrastive learning framework to learn binarized 1-bit representations for graphs, making balanced trade-offs between efficiency and performance. Details Abstract: While cont...
Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs (WSDM, 2023) [paper][code] Interpretable Research Interest Shift Detection with Temporal Heterogeneous Graphs (WSDM, 2023) [paper] Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks (AAAI, 20...
The results for the experiments on GOAT with products are much more erratic. As pictured below in the PageRank and GraphSAGE training runs, we observed spiking validation loss curves and even steadily climbing training loss across epochs. We suspect that the current hyperparameters are ill-fitted ...
Spiking neural networks (SNNs) are an efficient and energy-saving network with strong biological interpretation and great development prospects, helping GCNs work on mobile devices with strict power limits. However, the training effect of SNNs is still low compare to traditional CNN networks. In ...