随笔分类 - 论文
英文倾斜是原文,下划线是原文翻译
摘要:14 TEMPORAL GRAPH NETWORKS FOR DEEP LEARNING ON DYNAMIC GRAPHS link:https://scholar.google.com.hk/scholar_url?url=https://arxiv.org/pdf/2006.10637.pdf
阅读全文
摘要:12 Inductive Representation Learning on Temporal Graphs link:https://arxiv.org/abs/2002.07962 本文提出了时间图注意(TGAT)层,以有效地聚合时间-拓扑邻域特征,并学习时间-特征之间的相互作用。对于TGAT
阅读全文
摘要:11 GloDyNE Global Topology Preserving Dynamic Network Embedding link:http://arxiv.org/abs/2008.01935 Abstract 目前大多数现有的DNE方法的思想是捕捉最受影响的节点(而不是所有节点)或周围的拓
阅读全文
摘要:10 Exploring Temporal Information for Dynamic Network Embedding 5 link:https://scholar.google.com.sg/scholar_url?url=https://ieeexplore.ieee.org/abstr
阅读全文
摘要:9 Real-Time Streaming Graph Embedding Through Local Actions 11 link:https://scholar.google.com.sg/scholar_url?url=https://par.nsf.gov/servlets/purl/10
阅读全文
摘要:3 Dynamic Network Embedding by Modeling Triadic Closure Process link:https://scholar.google.com.sg/scholar_url?url=https://ojs.aaai.org/index.php/AAAI
阅读全文
摘要:7 Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks link:https://arxiv.org/abs/1908.01207 Abstract 本文提出了一种在嵌入空间中显示建模用户/项目的未来轨迹的
阅读全文
摘要:6 DyREP:Learning Representations Over Dynamic Graphs link:https://scholar.google.com/scholar_url?url=https://par.nsf.gov/servlets/purl/10099025&hl=zh-
阅读全文
摘要:5 Dynamic Graph Representation Learning Via Self-Attention Networks link:https://arxiv.org/abs/1812.09430 Abstract 提出了在动态图上使用自注意力 Conclusion 本文提出了使用自注
阅读全文
摘要:4 Streaming Graph Neural Networks link:https://dl.acm.org/doi/10.1145/3397271.3401092 Abstract 本文提出了一种新的动态图神经网络模型DGNN,它可以随着图的演化对动态信息进行建模。特别是,该框架可以通过捕获
阅读全文
摘要:2 DynGEM: Deep Embedding Method for Dynamic Graphs link:https://arxiv.org/abs/1805.11273v1 Abstract 首先这个嵌入是基于deep autoencoder的 该论文提出了三个主要优势: (1)随着时间的推
阅读全文
摘要:1 Continuous-Time Dynamic Network Embeddings Abstract 描述一种将时间信息纳入网络嵌入的通用框架,该框架提出了从CTDG中学习时间相关嵌入 Conclusion 描述了一个将时间信息纳入网络嵌入方法的通用框架。该框架为推广现有的基于随机游走
阅读全文
摘要:Abstract 惯例先说了一下原来的两种方法的优缺点 第一种 Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achiev
阅读全文

浙公网安备 33010602011771号