TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

An attempt at demystifying graph deep learning

87 pointsby jonathanbgnalmost 4 years ago

6 comments

joaoricoalmost 4 years ago
In case you&#x27;re interested in learning about graph deep learning, and are familiar with standard DL, I strongly recommend these two very good, recent books (freely available):<p>[1] Graph Representation Learning - William L. Hamilton <a href="https:&#x2F;&#x2F;www.cs.mcgill.ca&#x2F;~wlh&#x2F;grl_book&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.cs.mcgill.ca&#x2F;~wlh&#x2F;grl_book&#x2F;</a><p>[2] Deep Learning on Graphs - Yao Ma, Jilian Tang <a href="https:&#x2F;&#x2F;cse.msu.edu&#x2F;~mayao4&#x2F;dlg_book&#x2F;" rel="nofollow">https:&#x2F;&#x2F;cse.msu.edu&#x2F;~mayao4&#x2F;dlg_book&#x2F;</a>
d4rkp4tternalmost 4 years ago
A good survey paper is here (Jan 2021) by Chami, Abu-El-Haifa, Perozzi, Re and Murphy<p>[2005.03675] Machine Learning on Graphs: A Model and Comprehensive Taxonomy <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2005.03675" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2005.03675</a>
jcimsalmost 4 years ago
Super dumb question, when we talk about graph deep learning are we talking about deep learning with graphs is input? Or is it the use of graphs as the underlying architecture for a deep learning system.<p>I work in the field of information security and in my head I can see a scenario of using what I would call time series graphs, in which something like an attack or basic system behavior could be modeled as an evolution of relationships over time (implying some causality). Or maybe more precisely, they are a set of discrete graphs in which some edges are temporal proximity rather than a concrete relationship. My problem is I’m so illiterate when it comes to machine learning that I’m having trouble translating it into a basic context that I could start tinkering with to learn.<p>Part of the challenge comes from the fact that nearly every relationship or metric is discrete&#x2F;categorical in nature, there are very few continous&#x2F;scaler values when it comes to information that would be processed. As a result, most of the introductory tutorials and training around image classification or speech recognition or clustering are difficult to apply. I want to watch a billion events per hour to find instances where there are atypical relationships between system events in one log to network connection events in another. These graphs are extremely simple to compute, but categorizing them and analyzing them is proving difficult for my lay brain.
评论 #28074883 未加载
评论 #28073929 未加载
vsliraalmost 4 years ago
What&#x27;s the current killer app of GNNs? By that I mean, in which tasks is using a GNN-based approach obviously better?<p>Conceptually, just by framing the graph as a mxm matrix I assume the most obvious comparison would be against some sort of dimensionality reduction for node embedding. Should I see graph(node) embedding as an alternative to e.g. PCA, LDA, t-SNE and UMAP and variants?
评论 #28072314 未加载
评论 #28074098 未加载
评论 #28072825 未加载
评论 #28073903 未加载
评论 #28073949 未加载
d4rkp4tternalmost 4 years ago
Tangential — Curious how the author made those diagrams
评论 #28072311 未加载
bitcoinGod88almost 4 years ago
If you understand transformers, you understand the basics behind any neural &quot;graph network&quot; method. They are exceedingly simple
评论 #28072081 未加载
评论 #28071132 未加载