Combiner: Full Attention Transformer with Sparse Computation Cost.
Hongyu RenHanjun DaiZihang DaiMengjiao YangJure LeskovecDale SchuurmansBo DaiPublished in: NeurIPS (2021)
Keyphrases
- fuzzy logic
- storage cost
- high dimensional
- cost reduction
- compressed sensing
- visual attention
- cost sensitive
- dictionary learning
- efficient computation
- high cost
- communication cost
- efficiently computing
- cost savings
- sparse data
- genetic algorithm
- fault diagnosis
- sparse representation
- multi class
- query processing
- image sequences