graph-level problem

Data
Graph-Level Problems

In graph-level problems, there are multiple graphs. Each graph G represents a predictor associated with an observation yY. We assume that G,yp(G,y) and want to regress y on G.

Here, our hypothesis class is F={f(S)=k=1K1hkSk1|hkR}

Note

Since there are no graph signal observations, we use the vector of all ones 1 as our constant signal!

And our minimization problem is given by $$\min_{h_{k}} \frac{1}{m} \sum_{i=1}^M \ell\left( \sum_{k=0}^{K-1} h_{k} S^k \mathbb{1}, y \right)$$

Example

2025-02-03_graph-3.png
Suppose we want to predict the number of triangles incident to each node for any graph

In this example, since our output is an integer, it mades sense to use the 01 loss or a surrogate:

minhk1mi=1M(k=0K1hkSk1,y)

Application: automate triangle counting

Mentions

File
GINs are maximally powerful for anonymous input graphs
readout layer
2025-02-03 graphs lecture 4
2025-02-05 graphs lecture 5
2025-02-19 graphs lecture 9
2025-03-03 graphs lecture 11
2025-03-24 graphs lecture 14