Hyperdimensional computing speeds up multiple query processing together
Superposed Inference for Hyperdimensional Computing
Machine LearningArtificial Intelligence
Summary
Hyperdimensional computing is a way to quickly and reliably learn from data, but it usually has to process each new question one by one, which can be slow. The authors introduce a method called SupHDC that combines several questions before processing, saving time by sharing calculations. They use special keys to keep each question recognizable and separate, so predictions stay accurate. Their tests show faster speed with little to no loss in accuracy, including on small devices like Raspberry Pi.
What this means in practice
- •For embedded system developers: Run multiple machine learning queries more efficiently on resource-limited devices by sharing computation steps in hyperdimensional models.
- •For edge ai engineers: Improve inference speed for real-time, multi-query workloads on edge devices using lightweight query encoding and shared processing.
Authors
Quanling Zhao, Nilesh Prasad Pandey, Ye Tian, Tajana Rosing
Abstract
Hyperdimensional computing (HDC) is attractive for efficient and robust learning, but conventional inference still encodes every query independently, repeatedly paying the cost of high-dimensional projection. We introduce SupHDC, a new inference paradigm that processes multiple queries through a shared encoding computation. SupHDC assigns lightweight random slot keys, superposes the keyed queries before encoding, and uses slot-specific classifiers to recover their individual predictions. A random-feature kernel view explains why exact recovery of each hypervector is unnecessary: inference only needs to preserve the class evidence that determines the prediction. Across ten datasets, SupHDC achieves 1.39x analytical speedup with no average accuracy loss, and up to 2.08x speedup with only a 2.67 percentage-point mean accuracy loss. On a Raspberry Pi~5, it delivers 2.01x measured wall-clock speedup with a 2.26 percentage-point loss in mean prediction accuracy. SupHDC shows that high-dimensional redundancy can be used not only for robustness, but also as capacity for shared inference.