SGLDL adds new labels to a label-distribution model by keeping old label relations fixed in a scalable graph and compensating new-label gradients, giving the best Euclidean distance on IMDB-WIKI age bins.
Label distribution learning with label correlations on local samples,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Incremental Label Distribution Learning with Scalable Graph Convolutional Networks
SGLDL adds new labels to a label-distribution model by keeping old label relations fixed in a scalable graph and compensating new-label gradients, giving the best Euclidean distance on IMDB-WIKI age bins.