Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

Awon nkankikan Nẹtiwọọki adanwo

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

Jẹmọ itọsọna awọn ọnaAwon nkankikan Nẹtiwọọki
Ibeere 1 ti 8

Kini ẹrọ iširo pataki ti awọn nẹtiwọọki alayaworan pupọ julọ?

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  1. Kini ẹrọ iširo pataki ti awọn nẹtiwọọki alayaworan pupọ julọ?
    • Ifiranṣẹ ti nkọja ati akojọpọ laarin awọn apa adugbo
    • Sisun convolution lori akoj ẹbun ti o wa titi
    • Autoregressive tókàn-àmi asọtẹlẹ
    • Aileto rin pẹlu ko si eko
  2. Kilode ti iṣẹ ikojọpọ aládùúgbò GNN kan gbọdọ jẹ ailẹgbẹ permutation?
    • Lati ṣe ikẹkọ yiyara
    • Nitori a awonya ká aladugbo ni ko si atorunwa ibere
    • Nitori awọn aworan ti wa ni nigbagbogbo directed
    • Lati din awọn nọmba ti sile si ọkan
  3. Kini 'didun-ju' tọka si ni awọn GNN ti o jinlẹ?
    • Awọn aworan di blurry
    • Awonya ti o padanu egbegbe rẹ
    • Awọn ifisinu ipade ti n ṣajọpọ lati fẹrẹ jẹ aami bi awọn fẹlẹfẹlẹ ti n pọ si
    • Gradients exploding to ailopin
  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. Ninu GNN ti a lo si moleku kan, kini awọn apa ati awọn egbegbe ṣe aṣoju fun?
    • Awọn atomu ati awọn asopọ kemikali
    • Awọn piksẹli ati awọn awọ
    • Awọn ọrọ ati awọn gbolohun ọrọ
    • Awọn olumulo ati awọn ifiweranṣẹ
  6. Bawo ni ọpọlọpọ hops kuro le alaye ajo lọ si ipade kan lẹhin ti L ifiranṣẹ-ran fẹlẹfẹlẹ?
    • Nigbagbogbo gangan hop kan
    • Up to L hops
    • Gbogbo awonya ni kan nikan Layer
    • Odo 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