Graph Attention Networks · HackerPapers discussions

Graph Attention Networks — mentioned by paulmorio

Tue, 24 Jan 2023 21:56:11 GMT

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_tem...) 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. Starting out I would recommend implementing fundamental building blocks within whatever 'subculture' of ML you are interested in whether that be DL, kernel methods, probabilistic models, etc. Let's say you are interested in deep learning methods…

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

Graph Attention Networks — mentioned by nmca

Sun, 24 Jun 2018 19:29:06 GMT

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's hard), but people are actively working on it. Unitary neural nets, and the fast/slow weight paradigm are very different angles that seem promising. As for handling trees + graphs, this actually works very well. Thomas Kipf is pushing this…

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