paper-with-me

Papers

AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning

2019-04-08 · NAACL 2019 6 · Han Guo, Ramakanth Pasunuru, Mohit Bansal

Multi-task learning (MTL) has achieved success over a wide range of problems, where the goal is to improve the performance of a primary task using a set of relevant auxiliary tasks. However, when the usefulness of the auxiliary tasks w.r.t. the primary task is not known a priori, the success of MTL models depends on the correct choice of these auxiliary tasks and also a balanced mixing ratio of these tasks during alternate training. These two problems could be resolved via manual intuition or hyper-parameter tuning over all combinatorial task choices, but this introduces inductive bias or is not scalable when the number of candidate auxiliary tasks is very large. To address these issues, we present AutoSeM, a two-stage MTL pipeline, where the first stage automatically selects the most useful auxiliary tasks via a Beta-Bernoulli multi-armed bandit with Thompson Sampling, and the second stage learns the training mixing ratio of these selected auxiliary tasks via a Gaussian Process based Bayesian optimization framework. We conduct several MTL experiments on the GLUE language understanding tasks, and show that our AutoSeM framework can successfully find relevant auxiliary tasks and automatically learn their mixing ratio, achieving significant performance boosts on several primary tasks. Finally, we present ablations for each stage of AutoSeM and analyze the learned auxiliary task choices.

📄 PDF Abstract BibTeX arXiv:1904.04153

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian OptimizationInductive BiasMulti-Task LearningThompson Sampling

Similar Papers 제목 키워드 기반

GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks

2021-09-13 · EMNLP 2021 11 · Weicheng Ma, Renze Lou, Kai Zhang, Lili Wang 외

A key problem in multi-task learning (MTL) research is how to select high-quality auxiliary tasks automatically. This paper presents GradTS, an automatic auxiliary task selection method based on gradient calculation in T…

GPUMulti-Task LearningNatural Language Understanding

Efficient Online Data Mixing For Language Model Pre-Training

2023-12-05 · Alon Albalak, Liangming Pan, Colin Raffel, William Yang Wang

The data used to pretrain large language models has a decisive impact on a model's downstream performance, which has led to a large body of work on data selection methods that aim to automatically determine the most suit…

Language ModelingLanguage ModellingMMLU

Automatic music mixing with deep learning and out-of-domain data

2022-08-24 · Marco A. Martínez-Ramírez, Wei-Hsiang Liao, Giorgio Fabbro, Stefan Uhlich 외

Music mixing traditionally involves recording instruments in the form of clean, individual tracks and blending them into a final mixture using audio effects and expert knowledge (e.g., a mixing engineer). The automation …

Unmixing-Guided Spatial-Spectral Mamba with Clustering Tokens for Hyperspectral Image Classification

2026-04-10 · Yimin Zhu, Lincoln Linlin Xu arxiv

Although hyperspectral image (HSI) classification is critical for supporting various environmental applications, it is a challenging task due to the spectral-mixture effect, the spatial-spectral heterogeneity and the dif…

Hyperspectral Image Classification

UniGeM: Unifying Data Mixing and Selection via Geometric Exploration and Mining

2026-02-03 · Changhao Wang, Yunfei Yu, Xinhao Yao, Jiaolong Yang 외 arxiv

The scaling of Large Language Models (LLMs) is increasingly limited by data quality. Most methods handle data mixing and sample selection separately, which can break the structure in code corpora. We introduce \textbf{Un…