Conceptgraph context dilution
Mean-Pooling Graph Context Dilution
A problem in which, when an encoder uses mean pooling to aggregate a global graph vector, an increasing number of nodes causes newly added nodes to lower the contribution of key nodes, making the global vector increasingly smooth and losing discriminative information.
Timeline (last 90 days)
Oct 21
Using CVRP as a controlled proxy, the research team systematically identified three factors behind cross-scale generalization degradation: node density shift, attention diffusion, and dilution of graph context by mean pooling.
Unverified50%