REVIEW 1 cited by
Towards Memory-Efficient Training for Extremely Large Output Spaces -- Learning with 500k Labels on a Single Commodity GPU
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In classification problems with large output spaces (up to millions of labels), the last layer can require an enormous amount of memory. Using sparse connectivity would drastically reduce the memory requirements, but as we show below, it can result in much diminished predictive performance of the model. Fortunately, we found that this can be mitigated by introducing a penultimate layer of intermediate size. We further demonstrate that one can constrain the connectivity of the sparse layer to be uniform, in the sense that each output neuron will have the exact same number of incoming connections. This allows for efficient implementations of sparse matrix multiplication and connection redistribution on GPU hardware. Via a custom CUDA implementation, we show that the proposed approach can scale to datasets with 670,000 labels on a single commodity GPU with only 4GB memory.
Forward citations
Cited by 1 Pith paper
-
NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling
Dynamic sparse training of multiple heads on a shared backbone outperforms full dense ensembles on ImageNet and C4 while using less compute.
Discussion (0). Continue with ORCID to comment.