English
Related papers

Related papers: Single-dataset Experts for Multi-dataset Question …

200 papers

Dataset Distillation (DD) is a prominent technique that encapsulates knowledge from a large-scale original dataset into a small synthetic dataset for efficient training. Meanwhile, Pre-trained Models (PTMs) function as knowledge…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Yao Lu , Xuguang Chen , Yuchen Zhang , Jianyang Gu , Tianle Zhang , Yifan Zhang , Xiaoniu Yang , Qi Xuan , Kai Wang , Yang You

Often the best performing deep neural models are ensembles of multiple base-level networks, nevertheless, ensemble learning with respect to domain adaptive person re-ID remains unexplored. In this paper, we propose a multiple expert…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Yunpeng Zhai , Qixiang Ye , Shijian Lu , Mengxi Jia , Rongrong Ji , Yonghong Tian

Mixture-of-Experts (MoE) models substantially improve performance by increasing the capacity of dense architectures. However, directly training MoE models requires considerable computational resources and introduces extra overhead in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Jiacheng Ruan , Daize Dong , Xiaoye Qu , Tong Zhu , Ting Liu , Yuzhuo Fu , Yu Cheng , Suncheng Xiang

We consider a new problem of few-shot learning of compact models. Meta-learning is a popular approach for few-shot learning. Previous work in meta-learning typically assumes that the model architecture during meta-training is the same as…

Machine Learning · Computer Science 2022-10-19 Yong Wu , Shekhor Chanda , Mehrdad Hosseinzadeh , Zhi Liu , Yang Wang

In the field of few-shot learning (FSL), extensive research has focused on improving network structures and training strategies. However, the role of data processing modules has not been fully explored. Therefore, in this paper, we propose…

Machine Learning · Computer Science 2023-05-16 Wentao Hu , Xiurong Jiang , Jiarun Liu , Yuqi Yang , Hui Tian

Mixture-of-Experts (MoE) architectures have become standard in large language models, yet many of their core design choices - expert count, granularity, shared experts, load balancing, token dropping - have only been studied one or two at a…

Machine Learning · Computer Science 2026-05-13 Margaret Li , Sneha Kudugunta , Danielle Rothermel , Luke Zettlemoyer

We address the problem of ensemble selection in transfer learning: Given a large pool of source models we want to select an ensemble of models which, after fine-tuning on the target training set, yields the best performance on the target…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Andrea Agostinelli , Jasper Uijlings , Thomas Mensink , Vittorio Ferrari

Contaminated mixture of experts (MoE) is motivated by transfer learning methods where a pre-trained model, acting as a frozen expert, is integrated with an adapter model, functioning as a trainable expert, in order to learn a new task.…

Statistics Theory · Mathematics 2026-02-03 Fanqi Yan , Dung Le , Trang Pham , Huy Nguyen , Nhat Ho

Retrosynthesis is a problem to infer reactant compounds to synthesize a given product compound through chemical reactions. Recent studies on retrosynthesis focus on proposing more sophisticated prediction models, but the dataset to feed the…

Machine Learning · Computer Science 2020-10-05 Katsuhiko Ishiguro , Kazuya Ujihara , Ryohto Sawada , Hirotaka Akita , Masaaki Kotera

We propose an efficient knowledge transfer approach for model-based reinforcement learning, addressing the challenge of deploying large world models in resource-constrained environments. Our method distills a high-capacity multi-task agent…

Machine Learning · Computer Science 2025-07-04 Dmytro Kuzmenko , Nadiya Shvai

While transfer learning is an effective strategy, it often overlooks the opportunity to leverage knowledge from numerous available models online. Addressing this multi-source transfer learning problem is a promising path to boost…

Machine Learning · Computer Science 2026-04-24 Marcin Osial , Bartosz Wójcik , Bartosz Zieliński , Sebastian Cygert

A challenge in creating a dataset for machine reading comprehension (MRC) is to collect questions that require a sophisticated understanding of language to answer beyond using superficial cues. In this work, we investigate what makes…

Computation and Language · Computer Science 2018-08-29 Saku Sugawara , Kentaro Inui , Satoshi Sekine , Akiko Aizawa

While machine learning has emerged in recent years as a useful tool for rapid prediction of materials properties, generating sufficient data to reliably train models without overfitting is still impractical for many applications. Towards…

Materials Science · Physics 2022-07-29 Rees Chang , Yu-Xiong Wang , Elif Ertekin

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…

Computation and Language · Computer Science 2020-10-13 Fahimeh Saleh , Wray Buntine , Gholamreza Haffari

We propose JEDI, a multi-dataset semi-supervised learning method, which efficiently combines knowledge from multiple experts, learned on different datasets, to train and improve the performance of individual, per dataset, student models.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Lucian Bicsi , Bogdan Alexe , Radu Tudor Ionescu , Marius Leordeanu

Few-shot learning, which aims at extracting new concepts rapidly from extremely few examples of novel classes, has been featured into the meta-learning paradigm recently. Yet, the key challenge of how to learn a generalizable classifier…

Machine Learning · Computer Science 2019-10-08 Limeng Qiao , Yemin Shi , Jia Li , Yaowei Wang , Tiejun Huang , Yonghong Tian

Traditional models grounded in first principles often struggle with accuracy as the system's complexity increases. Conversely, machine learning approaches, while powerful, face challenges in interpretability and in handling physical…

Machine Learning · Computer Science 2024-01-31 Jessica Leoni , Valentina Breschi , Simone Formentin , Mara Tanelli

Although transfer learning has been shown to be successful for tasks like object and speech recognition, its applicability to question answering (QA) has yet to be well-studied. In this paper, we conduct extensive experiments to investigate…

Computation and Language · Computer Science 2018-04-24 Yu-An Chung , Hung-Yi Lee , James Glass

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects the experts, all the…

Machine Learning · Computer Science 2025-05-27 Shibo Jie , Yehui Tang , Kai Han , Yitong Li , Duyu Tang , Zhi-Hong Deng , Yunhe Wang

The main goal behind state-of-the-art pre-trained multilingual models such as multilingual BERT and XLM-R is enabling and bootstrapping NLP applications in low-resource languages through zero-shot or few-shot cross-lingual transfer.…

Computation and Language · Computer Science 2020-10-07 Jonas Pfeiffer , Ivan Vulić , Iryna Gurevych , Sebastian Ruder