Small-Data Learning

Follow this topic Ask about this topic

Latest papers

10 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

SPD-MetaFormer is what you need for small-data brain decoding
Oct 7, 2026Zhida Wang, Wei Lyu, Guo Yu +1Small-Data Learning EEG Decoding
Can Domain Generalization be Guaranteed in Small-Sample Learning?
Sep 30, 2026Hong ZhengDomain Generalization Small-Data Learning
This work was completed during my Ph.D. period and was the result of a flash of inspiration. I decided to submit it to arXiv and leave its value to the readers.
A Kernel-Based Modular Discriminant Analysis Framework for Small-Sample Learning
Sep 9, 2026Lingxiao Qu, Yan PeiSmall-Data Learning Kernel Methods
Graduate School of Computer Science and Engineering, University of Aizu, 90 Kamiiawase, Tsuruga, Ikki-machi, Aizuwakamatsu, 965-8580, Fukushima, Japan · Computer Science Division, University of Aizu, 90 Kamiiawase, Tsuruga, Ikki-machi, Aizuwakamatsu, 965-8580, Fukushima, Japan
Physics-Informed Machine Learning Under Small-Data Constraints: Lessons from Abrasive Waterjet Milling
Jul 8, 2026Sarah Grewe, Jörg FrochteSurrogate Modeling Residual Learning
Bochum University of Applied Sciences Germany
Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines
May 21, 2026David Mendez, Fernando Martin-Maroto, Gonzalo G. de PolaviejaClassification Image Classification
Mathematics of Behavior and Intelligence Lab, Champalimaud Foundation, Lisbon
Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases
May 19, 2026Jingwen Liu, Ezra Edelman, Surbhi Goel +1Deep Learning Optimization Statistical Learning Theory
Columbia University · University of Pennsylvania · Kempner Institute, Harvard University
Genetic algorithm vs. gradient descent for training a neural network architecture dedicated to low data regimes in small medical datasets
May 13, 2026Amine Boukhari, Boglarka Ecsedi, Laszlo Papp +1Gradient Descent Neural Network Optimization
Laboratory of medical information processing (LaTIM), INSERM, UMR 1101,university of western brittany · Center for Medical Physics and Biomedical Engineering, Medical University of Vienna · Georgia Institute of Technology
GRMLR: Knowledge-Enhanced Small-Data Learning for Deep-Sea Cold Seep Stage Inference
Mar 25, 2026Chenxu Zhou, Zelin Liu, Rui Cai +7Small-Data Learning Data-Efficient Learning
Shanghai Jiao Tong University, 200240 Shanghai, China
Machine Learning Models to Identify Promising Nested Antiresonance Nodeless Fiber Designs
Mar 2, 2026Rania A. Eltaieb, Sophie LaRochelle, Leslie A. RuschSmall-Data Learning Data-Efficient Learning
Predictive Inorganic Synthesis based on Machine Learning using Small Data sets: a case study of Hydrodynamic Diameter-controlled Cu Nanoparticles
Dec 18, 2025Brent Motmans, Digvijay Ghogare, Thijs G. I. van Wijk +6Small-Data Learning Materials Property Prediction
Hasselt University, Institute for Materials Research (IUMAT), Quantum & Artificial inTelligence design Of Materials (QuATOMs), Martelarenlaan 42, B-3500 Hasselt, Belgium · Hasselt University, Institute for Materials Research (IUMAT), Hybrid Materials Design (HyMaD), Martelarenlaan 42, B-3500 Hasselt, Belgium · imec, IUMAT, Wetenschapspark 1, B-3590 Diepenbeek, Belgium +4

Oct 7, 2026J/K move · Enter open · S save

SPD-MetaFormer is what you need for small-data brain decoding

Zhida Wang, Wei Lyu, Guo Yu, Sui Tang

Small-Data Learning EEG Decoding Attention Mechanisms Riemannian Geometry Data-Efficient Learning

Open paper AskPDF arXiv

Brain signal decoding is challenging because neural recordings are noisy and vary across individuals, while labeled data are often limited. Recent attention-based models on the symmetric positive definite (SPD) manifold have nevertheless achieved strong performance using covariance and connectivity representations, yet the contribution of learned token weighting remains unclear. We examine two representative architectures, MAtt (based on log-Euclidean geometry) and GBWAtt (based on generalized Bures--Wasserstein geometry), and find that their learned attention weights remain close to uniform after training. We relate this behavior to bounded similarity parameterizations that, under the original softmax scaling, limit attention-weight contrast. Moreover, replacing learned weights with uniform weights, throughout training and evaluation, has little effect on mean predictive performance while preserving each model's original aggregation geometry. Motivated by these findings, we introduce SPD-MetaFormer, an attention-free architecture built on uniformly weighted Fréchet aggregation under log-Euclidean geometry. Its backbone uses a geodesic residual to update a summary token and a shared spectral feedforward map to transform all tokens, followed by a learned weighted readout. Token states remain SPD-valued until tangent-space classification. Across three EEG benchmarks, SPD-MetaFormer achieves competitive results relative to published Euclidean and manifold baselines. Separate matched reproductions test learned versus uniform weighting within MAtt and GBWAtt. These results suggest that, in the short-sequence and limited-data regimes studied, carefully designed SPD architectures can provide a simpler and effective alternative to adaptive manifold attention.