2024年4月23日 · 受超图扩散算法的启发，本工作提出了一种新的HNN架构，命名为ED-HNN，它可以可证地逼近任何连续等变超图扩散算子，可以模拟各种高阶关系。 ED-HNN可以通过将超图的星形扩展与标准消息传递神经网络相结合来有效实现。 ED-HNN在处理异性超图和构建深层模型方面显示出很大的优势。 作者在九个真实超图数据集上对ED-HNN进行了节点分类评估。 ED-HNN在这九个数据集上均优于最佳基线，并在其中四个数据集上的预测准确率提高了超过2%。 介绍. …

2024年4月1日 · As networks of HOIs are expressed mathematically as hypergraphs, hypergraph neural networks (HNNs) have emerged as a powerful tool for representation learning on hypergraphs. Given the emerging trend, we present the first survey dedicated to HNNs, with an in-depth and step-by-step guide.

In this article, we propose a simple discrete model of self-connectionless HNN in which two heterogeneous neurons have different activation functions of sine and hyperbolic tangent.

2023年12月31日 · As networks of HOIs are expressed mathematically as hypergraphs, hypergraph neural networks (HNNs) have emerged as a powerful tool for representation learning on hypergraphs. Given the emerging trend, we present the first survey dedicated to HNNs, with an in-depth and step-by-step guide.

2023年10月29日 · Abstract: The progress in hyperbolic neural networks (HNNs) research is hindered by their absence of inductive bias mechanisms, which are essential for generalizing to new tasks and facilitating scalable learning over large datasets. In this paper, we aim to alleviate these issues by learning generalizable inductive biases from the nodes' local ...

Our experiments demonstrate that clipped HNNs become super-hyperbolic classifiers: They are not only consistently better than HNNs which already outperform ENNs on hierarchical data, but also on-par with ENNs on MNIST, CIFAR10, CIFAR100 and ImageNet benchmarks, with better adversarial robustness and out-of-distribution detection.

2024年3月28日 · 近期，清华大学类脑计算研究中心 赵蓉 教授团队和 施路平 教授团队合作在 《国家科学评论》 （National Science Review, NSR） 发表了 关于混合神经网络 （Hybrid Neural Network, HNN） 的系统性综述，从起源、概念、构建框架到支撑系统，全面阐述了HNN的发展脉络与未来方向。 人类大脑具有卓越的通用智能和出色的低功耗特性，一直都是智能领域不断追求与仿效的典范。 基于这一深刻洞察，类脑计算应运而生，这一新兴的计算范式借鉴了大脑的基 …

2024年2月4日 · In this paper, we propose a benchmark for evaluating HRC and conduct a comprehensive analysis of why HNNs are effective through large-scale experiments. Inspired by the analysis results, we propose several pre-training strategies to enhance HRC and improve the performance of downstream tasks, further validating the reliability of the analysis.

2024年2月26日 · 清华大学类脑计算研究中心 赵蓉 教授团队和 施路平 教授团队合作在《国家科学评论》（National Science Review, NSR）发表了 关于混合神经网络（Hybrid Neural Network, HNN）的系统性综述，从起源、概念、构建框架到支撑系统，全面阐述了HNN的发展脉络与未来方向。 HNN将神经科学范式的脉冲神经网络（Spiking Neural Network,...

2024年12月1日 · Our recent paper, “Training Hamiltonian neural networks without backpropagation”, introduces an approach that does just that. By leveraging data-driven methods, we achieve both high accuracy and high speed in training HNNs. Here’s a deep dive into the ideas, methods and results that make this work so exciting.