A Comprehensive Survey on Graph Neural Networks · HackerPapers discussions

A Comprehensive Survey on Graph Neural Networks — mentioned by andreyk

Mon, 09 May 2022 19:10:43 GMT

A survey paper is usually a good way to go, such as A comprehensive survey on graph neural networks (https://arxiv.org/abs/1901.00596) or Graph Neural Networks: A Review of Methods and Applications (https://arxiv.org/abs/1812.08434)

Paper and discussion history. A mention is not an endorsement.

A Comprehensive Survey on Graph Neural Networks — mentioned by nl

Mon, 17 Feb 2020 22:46:22 GMT

On the contrary, Graph NN's I've found Graph NNs extraordinarily useful and very easy to train! I'm not sure what kind of problems you are trying to use them for, but generally they are really useful for node classification or recommendation type tasks. So for example in the knowledge graph context, you can do things like give it a tiger, jaguar and panther and it will find nodes like lions and leopards. https://arxiv.org/pdf/1901.00596.pdf is a survey paper which has a decent overview of the tasks they are useful for. http://research.baidu.com/Public/uploads/5c1c9a58317b3.pdf is using them…

Paper and discussion history. A mention is not an endorsement.

A Comprehensive Survey on Graph Neural Networks — mentioned by tastroder

Sun, 16 Feb 2020 20:09:24 GMT

> At which NLP tasks are they state the art? The only one where they are really competitive is dependency parsing. (from my own disjonction of cases) At tasks that actually involve graphs presumably. https://arxiv.org/pdf/1901.00596.pdf https://paperswithcode.com/task/graph-classification has a bunch of GNNs ranked #1 > Also were there any new real SOTA on any NLP tasks since last summer? I feel like accuracy progress has frozen.. That's pretty normal for winter/spring, it's not conference season.

Paper and discussion history. A mention is not an endorsement.

A Comprehensive Survey on Graph Neural Networks — mentioned by visarga

Tue, 08 Jan 2019 08:14:20 GMT

Graph network reviews seem all the rage, here's another recent one: "A Comprehensive Survey on Graph Neural Networks " https://arxiv.org/abs/1901.00596

Paper and discussion history. A mention is not an endorsement.

A Comprehensive Survey on Graph Neural Networks — HN submission

Mon, 07 Jan 2019 00:25:00 GMT

A Comprehensive Survey on Graph Neural Networks (2019)

19 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.