Multi-label HD Classification in 3D Flash

2020 IFIP/IEEE 28th International Conference on Very Large Scale Integration (VLSI-SOC)(2020)

引用 1|浏览14
Many classification problems in practice map each sample to more than one label - this is known as multi-label classification. In this work, we present Multi-label HD, an in 3D storage multi-label classification system that uses Hyperdimensional Computing (HD). Multi-label HD is the first HD system to support multi-label classification. We propose two different mappings of HD to Multi-label HD. The first, Power Set HD, transforms the multi-label problem into single-label classification by creating a new class for each label combination. The second, Multi-Model HD, creates a binary classification model for each possible label. Our evaluation shows that Multi-Model HD achieves, on average, 47.8× higher energy efficiency and 47.1× faster execution time while achieving 5% higher classification accuracy as state-of-the-art light-weight multi-label classifiers. Power Set HD achieves 13% higher accuracy than Multi-Model HD, but is 2× slower. Our 3D-flash acceleration further improves the energy efficiency of Multi-label HD training by 228× and reduces the latency by 610× vs training on a CPU.
MultiModel HD,state-of-the-art light-weight multilabel classifiers,Power Set HD,Multilabel HD training,Multilabel HD classification,classification problems,3D storage multilabel classification system,HD system,multilabel problem,single-label classification,label combination,binary classification model,possible label
AI 理解论文