paper-with-me

홈 › Papers

Multitask Extension of Geometrically Aligned Transfer Encoder

2024-05-03 · Sung Moon Ko, Sumin Lee, Dae-Woong Jeong, Hyunseung Kim, Chanhui Lee, Soorin Yim, Sehui Han

Molecular datasets often suffer from a lack of data. It is well-known that gathering data is difficult due to the complexity of experimentation or simulation involved. Here, we leverage mutual information across different tasks in molecular data to address this issue. We extend an algorithm that utilizes the geometric characteristics of the encoding space, known as the Geometrically Aligned Transfer Encoder (GATE), to a multi-task setup. Thus, we connect multiple molecular tasks by aligning the curved coordinates onto locally flat coordinates, ensuring the flow of information from source tasks to support performance on target data.

📄 PDF Abstract BibTeX arXiv:2405.01974

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks

2023-10-10 · Sung Moon Ko, Sumin Lee, Dae-Woong Jeong, Woohyung Lim 외

Transfer learning is a crucial technique for handling a small amount of data that is potentially related to other abundant data. However, most of the existing methods are focused on classification tasks using images and …

regressionTransfer Learning

Deep Asymmetric Multi-task Feature Learning

2017-08-01 · ICML 2018 7 · Hae Beom Lee, Eunho Yang, Sung Ju Hwang

We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen in the feature sharing p…

image-classificationImage ClassificationTransfer Learning

Task Addition in Multi-Task Learning by Geometrical Alignment

2024-09-25 · Soorin Yim, Dae-Woong Jeong, Sung Moon Ko, Sumin Lee 외

Training deep learning models on limited data while maintaining generalization is one of the fundamental challenges in molecular property prediction. One effective solution is transferring knowledge extracted from abunda…

Molecular Property PredictionMulti-Task LearningProperty Prediction

Transferable speech-to-text large language model alignment module

2024-06-19 · Boyong Wu, Chao Yan, Haoran Pu

By leveraging the power of Large Language Models(LLMs) and speech foundation models, state of the art speech-text bimodal works can achieve challenging tasks like spoken translation(ST) and question answering(SQA) altoge…

Language ModelingLanguage ModellingLarge Language ModelQuestion Answering+1

Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders

2025-09-26 · Jake S. Rhodes, Adam G. Rustad, Marshall S. Nielsen, Morgan Chase McClellan 외 arxiv

Manifold alignment (MA) involves a set of techniques for learning shared representations across domains, yet many traditional MA methods are incapable of performing out-of-sample extension, limiting their real-world appl…

Representation LearningDomain Generalization