Tree Methods for Hierarchical Classification in Parallel
This work addresses the computational bottleneck in hierarchical classification for large-scale semantic trees, such as WordNet, by enabling efficient parallel processing on hardware accelerators.
The paper tackles the problem of efficiently performing hierarchical classification in parallel by transforming classification scores and labels to ancestral paths using tensor operations, achieving negligible computation and a fixed memory overhead of 0.04GB on a dataset with 117,659 classes.
We propose methods that enable efficient hierarchical classification in parallel. Our methods transform a batch of classification scores and labels, corresponding to given nodes in a semantic tree, to scores and labels corresponding to all nodes in the ancestral paths going down the tree to every given node, relying only on tensor operations that execute efficiently on hardware accelerators. We implement our methods and test them on current hardware accelerators with a tree incorporating all English-language synsets in WordNet 3.0, spanning 117,659 classes in 20 levels of depth. We transform batches of scores and labels to their respective ancestral paths, incurring negligible computation and consuming only a fixed 0.04GB of memory over the footprint of data.