5 papers · 1 filter
GRAIL: Post-hoc Compensation by Linear Reconstruction for Compressed Networks
Wenwu Tang, Dong Wang, Lothar Thiele +1
Structured deep model compression methods are hardware-friendly and substantially reduce memory and inference costs. However, under aggressive compression, the resulting accuracy d…
Cut Less, Fold More: Model Compression through the Lens of Projection Geometry
Olga Saukh, Dong Wang, Haris Šikić +2
Compressing neural networks without retraining is vital for deployment at scale. We study calibration-free compression through the lens of projection geometry: structured pruning i…
Physics-Guided Inductive Spatiotemporal Kriging for PM2.5 with Satellite Gradient Constraints
Shuo Wang, Mengfan Teng, Yun Cheng +8
High-resolution mapping of fine particulate matter (PM2.5) is a cornerstone of sustainable urbanism but remains critically hindered by the spatial sparsity of ground monitoring net…
PCDCNet: A Surrogate Model for Air Quality Forecasting with Physical-Chemical Dynamics and Constraints
Shuo Wang, Yun Cheng, Qingye Meng +6
Air quality forecasting (AQF) is critical for public health and environmental management, yet remains challenging due to the complex interplay of emissions, meteorology, and chemic…
Forget the Data and Fine-Tuning! Just Fold the Network to Compress
Dong Wang, Haris Šikić, Lothar Thiele +1
We introduce model folding, a novel data-free model compression technique that merges structurally similar neurons across layers, significantly reducing the model size without the…