Graphs and Relational Learning
Pass measurements through one graph layer
BOTIE
Examples, experiments and workspace controls
Connect a tool's inputs to see what it produces. You can try a branch before connecting it to Result.
Try your own inputs
Use a copy of the example to try your own data. Keep the problem's assumptions in mind, and predict the effect of a change before checking the output. You can also add another branch to compare two ways of doing the calculation.
Context for this challenge
Add identity to adjacency, normalise symmetrically, and multiply by the feature rows.
Botie has an undirected adjacency matrix, node features, and supplied feature weights.
Inspect the component calculation
Matrix multiplication(
Left matrix: Scale by both endpoint degrees(
Adjacency including self-loops: Add self-connections(
Adjacency matrix: Undirected adjacency, zero diagonal
)
)
Right matrix: Node feature rows
)Examples and results
- Undirected adjacency, zero diagonal
0 1 1 0 - Node feature rows
2 4 - Required result
3 3
- Undirected adjacency, zero diagonal
0 1 1 0 - Node feature rows
2 4 - Required result
3 3
Try a fresh construction
This clears this draft, including its undo history. Earlier successful attempts stay recorded. Build again without opening hints to record an independent attempt.
Stuck? Inspect a worked construction
The tools below form one possible solution. You can assemble it, follow its signals, and undo that change to return to your own construction.
Assumptions and test precision
This is one forward layer with supplied weights. Symmetric scaling assumes a non-negative undirected graph. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.
Your last tested pieces can start the full construction. An existing draft there keeps its own pieces.
Every node can hear the whole triangle
This check uses the pieces from “Separate graph mixing from feature mixing”.
BOTIE
- Undirected adjacency, zero diagonal
0 1 1 1 0 1 1 1 0 - Node feature rows
0 3 6 - Shared feature weights
1
Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.
Build a construction in the workspace above first. This case will test those pieces.
Which matrix controls information exchange between pumps, and which controls feature combinations?
A forward graph layer uses supplied weights; learning them requires a separate objective and training procedure.
This is one forward layer with supplied weights. Symmetric scaling assumes a non-negative undirected graph.
Work through the Python challenges →