SVQ: Sparse Vector Quantization for Spatiotemporal Forecasting
Chen, Chao, Zhou, Tian, Zhao, Yanjun, Liu, Hui, Sun, Liang, Jin, Rong
–arXiv.org Artificial Intelligence
Spatio-temporal forecasting, pivotal in numerous fields, hinges on the delicate equilibrium between isolating nuanced patterns and sifting out noise. To tackle this, we introduce Sparse Regression-based Vector Quantization (SVQ), a novel technique that leverages sparse regression for succinct representation, an approach theoretically and practically favored over classical clustering-based vector quantization methods. This approach preserves critical details from the original vectors using a regression model while filtering out noise via sparse design. Moreover, we approximate the sparse regression process using a blend of a two-layer MLP and an extensive codebook. This approach not only substantially cuts down on computational costs but also grants SVQ differentiability and training simplicity, resulting in a notable enhancement of performance. Our empirical studies on five spatial-temporal benchmark datasets demonstrate that SVQ achieves state-of-the-art results. Specifically, on the WeatherBench-S temperature dataset, SVQ improves the top baseline by 7.9%. In video prediction benchmarks-Human, KTH, and KittiCaltech-it reduces MAE by an average of 9.4% and improves image quality by 17.3% (LPIPS).
arXiv.org Artificial Intelligence
Feb-7-2024
- Country:
- North America
- United States
- Washington > King County
- Seattle (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.05)
- Florida > Miami-Dade County
- Miami (0.04)
- California
- San Francisco County > San Francisco (0.14)
- Los Angeles County > Long Beach (0.04)
- Washington > King County
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- United States
- Europe
- Asia
- China (0.04)
- Middle East > Israel
- Haifa District > Haifa (0.04)
- North America
- Genre:
- Research Report (1.00)
- Technology: