Summary of Smore: Similarity-based Hyperdimensional Domain Adaptation For Multi-sensor Time Series Classification, by Junyao Wang et al.
SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classification
by Junyao Wang, Mohammad Abdullah Al Faruque
First submitted to arxiv on: 20 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel resource-efficient domain adaptation algorithm for multi-sensor time series classification, called SMORE. The algorithm leverages hyperdimensional computing to efficiently and parallelly operate on the data. It dynamically customizes test-time models by considering the domain context of each sample to mitigate the negative impacts of distribution shift. SMORE achieves 1.98% higher accuracy than state-of-the-art DNN-based DA algorithms, while being 18.81x faster in training and 4.63x faster in inference. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to make machines learn from data that’s different from what they were trained on. This is important because often the data collected by sensors changes over time or varies between locations, which can cause the machine learning models to fail. The researchers created an algorithm called SMORE that helps these models adapt to the changing data without needing a lot of extra power or resources. |
Keywords
* Artificial intelligence * Classification * Domain adaptation * Inference * Machine learning * Time series
