Guide-yakabatana mibvunzo · Pakati Nhanho

Grafu Neural Networks Quiz

Review GNN message passing, permutation invariance, over-smoothing, attention, molecular graphs, and receptive-field hops.

Nzira dzekutungamira dzinoenderanaGrafu Neural Networks
Mubvunzo 1 ye 8

Ndeipi yakakosha computational maitiro eakawanda magirafu neural network?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Ndeipi yakakosha computational maitiro eakawanda magirafu neural network?
    • Kupfuura meseji uye kuunganidzwa pakati penzvimbo dzakavakidzana
    • Kutsvedza convolution pamusoro peiyo yakagadziriswa pixel grid
    • Autoregressive inotevera-chiratidzo kufanotaura
    • Random anofamba asina kudzidza
  2. Sei GNN's muvakidzani-aggregation basa richifanira kunge risingachinjike?
    • Kuita kuti kudzidzisa kukurumidze
    • Nekuti vavakidzani vegirafu havana maodha ekuzvarwa
    • Nokuti magirafu anogara achitungamirirwa
    • Kuderedza nhamba yeparameters kune imwe
  3. Chii chinonzi 'over-smoothing' chinoreva mune zvakadzama maGNN?
    • Mifananidzo iri kudzima
    • Girafu inorasika mipendero
    • Node embeddings inochinjika kuita inenge yakafanana sezvo maseru achiwedzera
    • Gradients kuputika kusvika kusingagumi
  4. How does a Graph Attention Network differ from a basic GCN layer?
    • It removes all graph edges before message passing
    • It assigns each node a unique text token
    • It guarantees deeper networks cannot over-smooth
    • It learns attention coefficients for neighbors, while the GCN uses degree-normalized propagation weights
  5. MuGNN inoshandiswa kunemorekuru, node nemapendero zvinombomirirei?
    • Maatomu uye zvisungo zvemakemikari
    • Pixels uye mavara
    • Mazwi nemitsara
    • Vashandisi uye zvinotumirwa
  6. Mangani mahops kure anogona kuenda kune node mushure meL meseji-inopfuudza maseru?
    • Nguva dzose hop imwe chete
    • Kusvika kuL hops
    • Girafu yose muchikamu chimwe chete
    • Zero hops
  7. What makes GraphSAGE an inductive graph-learning method?
    • It stores a separate free parameter vector for every possible test node
    • It requires one fixed graph and cannot process new nodes
    • It learns neighborhood aggregation functions that can be applied to unseen nodes
    • It replaces node features with graph-level labels
  8. In the original GCN propagation rule, what does symmetric degree normalization do to adjacency messages?
    • Sorts neighboring nodes alphabetically
    • Deletes every edge with a low feature value
    • Makes the graph directed by reversing all edges
    • Scales each edge contribution using the inverse square roots of the source and target node degrees