public:grl_readingmemo
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revision | |||
public:grl_readingmemo [2024/04/04 15:34] – [#01, liangz] liang | public:grl_readingmemo [2024/04/04 16:12] (current) – liang | ||
---|---|---|---|
Line 61: | Line 61: | ||
p5: | p5: | ||
* applications: | * applications: | ||
- | * difference from a standard supervised learning | + | * difference from a standard supervised learning: the assumption/ |
+ | * popular inductive bias used in graph learning: homophily (same attrubute with neighbors), structural equivalence (similar local structure -> similar label), heterophily (e.g., gender). | ||
+ | |||
+ | p6: | ||
+ | * supervised learning and semi-supervised learning, and GL (no iid assumption) | ||
+ | * relation prediction: e.g., recommendation system, side-effect. Notice the requirement of inductive bias. | ||
+ | |||
+ | p7: | ||
+ | * clustering and community detection | ||
+ | * graph classification, | ||
+ | |||
+ | p8: | ||
+ | * iid assumption and why? -> Li-Yang | ||
+ | * Additional comment: Causal relation and correlation. ML is often consider the latter approach but actually we need to consider the former. |
public/grl_readingmemo.1712212462.txt.gz · Last modified: 2024/04/04 15:34 by liang