按年被提到
20172018 · 1 次2026
机器学习与深度学习›神经网络架构探索·arXiv:1710.10903 · stat.ML

Graph Attention Networks

Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2018-06-24 · 最近 2023-01-24
2不同的人
2活跃月份
2讨论串
17,337被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论nmca · 2018-06

“The latter of those two points is much more valid than the former. You're comment about generalisation difficulty is pretty accurate, but as for "sucks at variable length data", I think neural machine translation [0] and the fact that schemes including RNNs just won M4 [1] indicate that this is incorrect. Your point about remembering the past is true (it'…”

Ted Nelson struggles with uncomprehending radio interviewer (1979) [audio]原评论 ↗
评论paulmorio · 2023-01

“I have done this a few times now. Alone (e.g. https://github.com/paulmorio/geo2dr) and in collaboration with others (e.g. https://github.com/benedekrozemberczki/pytorch_geometric_temporal) primarily as a way to learn about the methods I was interested in from a research perspective whilst improving my skills in software engineering. I am still learning. …”

Ask HN: ML Papers to Implement原评论 ↗