Re:TensorFlow Graph Neural Networks
by lmeyerov on Thursday November 18, 2021 @07:22PM
(#29272352)
Yes I think you are seeing it
Before: People might precompute graph scores ("pagerank", ...) and use as features for tabular NNs. Or use simpler and slow GNNs like GraphSAGE bc the domain fit was great (ex: Pinterest social recs)
After: heterogeneity and scale for graphs that fit in CPU RAM (1TB) w decent GPUs
Re:unrolling, yeah a bunch of papers there :) sampling, artificial jump edges, and adversarial techniques have been helping with aspects of generalization (far data, unbalanced data, ...)
Before: People might precompute graph scores ("pagerank", ...) and use as features for tabular NNs. Or use simpler and slow GNNs like GraphSAGE bc the domain fit was great (ex: Pinterest social recs)
After: heterogeneity and scale for graphs that fit in CPU RAM (1TB) w decent GPUs
Re:unrolling, yeah a bunch of papers there :) sampling, artificial jump edges, and adversarial techniques have been helping with aspects of generalization (far data, unbalanced data, ...)