paper-with-me

홈 › Papers

AdaCap: An Adaptive Contrastive Approach for Small-Data Neural Networks

2025-11-25 · Bruno Belucci, Karim Lounici, Katia Meziani arxiv

Neural networks struggle on small tabular datasets, where tree-based models remain dominant. We introduce Adaptive Contrastive Approach (AdaCap), a training scheme that combines a permutation-based contrastive loss with a Tikhonov-based closed-form output mapping. Across 85 real-world regression datasets and multiple architectures, AdaCap yields consistent and statistically significant improvements in the small-sample regime, particularly for residual models. A meta-predictor trained on dataset characteristics (size, skewness, noise) accurately anticipates when AdaCap is beneficial. These results show that AdaCap acts as a targeted regularization mechanism, strengthening neural networks precisely where they are most fragile. All results and code are publicly available at https://github.com/BrunoBelucci/adacap.

📄 PDF Abstract BibTeX arXiv:2511.20170

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AdaCap: Adaptive Capacity control for Feed-Forward Neural Networks

2022-05-09 · Katia Meziani, Karim Lounici, Benjamin Riu

The capacity of a ML model refers to the range of functions this model can approximate. It impacts both the complexity of the patterns a model can learn but also memorization, the ability of a model to fit arbitrary labe…

Memorization

TADACap: Time-series Adaptive Domain-Aware Captioning

2025-04-15 · Elizabeth Fons, Rachneet Kaur, Zhen Zeng, Soham Palande 외

While image captioning has gained significant attention, the potential of captioning time-series images, prevalent in areas like finance and healthcare, remains largely untapped. Existing time-series captioning methods t…

Image CaptioningRetrievalTime Series

Adaptive Multi-User Channel Estimation Based on Contrastive Feature Learning

2023-03-06 · Yihan Xu, Lixiang Lian

Correlation exploitation is essential for efficient multi-user channel estimation (MUCE) in massive MIMO systems. However, the existing works either rely on presumed strong correlation or learn the correlation through la…

Contrastive Learning

Adversarial Contrastive Distillation with Adaptive Denoising

2023-02-17 · Yuzheng Wang, Zhaoyu Chen, Dingkang Yang, Yang Liu 외

Adversarial Robustness Distillation (ARD) is a novel method to boost the robustness of small models. Unlike general adversarial training, its robust knowledge transfer can be less easily restricted by the model capacity.…

Adversarial RobustnessDenoisingTransfer Learning

Adversarial Lagrangian Integrated Contrastive Embedding for Limited Size Datasets

2022-10-06 · Amin Jalali, Minho Lee

Certain datasets contain a limited number of samples with highly various styles and complex structures. This study presents a novel adversarial Lagrangian integrated contrastive embedding (ALICE) method for small-sized d…