paper-with-me

Papers

Uncertainty Regularized Multi-Task Learning

2022-05-01 · WASSA (ACL) 2022 5 · Kourosh Meshgi, Maryam Sadat Mirzaei, Satoshi Sekine

By sharing parameters and providing task-independent shared features, multi-task deep neural networks are considered one of the most interesting ways for parallel learning from different tasks and domains. However, fine-tuning on one task may compromise the performance of other tasks or restrict the generalization of the shared learned features. To address this issue, we propose to use task uncertainty to gauge the effect of the shared feature changes on other tasks and prevent the model from overfitting or over-generalizing. We conducted an experiment on 16 text classification tasks, and findings showed that the proposed method consistently improves the performance of the baseline, facilitates the knowledge transfer of learned features to unseen data, and provides explicit control over the generalization of the shared model.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learningtext-classificationText ClassificationTransfer Learning

Similar Papers 제목 키워드 기반

Quantifying Classification Uncertainty using Regularized Evidential Neural Networks

2019-10-15 · Xujiang Zhao, Yuzhe Ou, Lance Kaplan, Feng Chen 외

Traditional deep neural nets (NNs) have shown the state-of-the-art performance in the task of classification in various applications. However, NNs have not considered any types of uncertainty associated with the class pr…

ClassificationGeneral Classification

Entropy-regularized Point-based Value Iteration

2024-02-14 · Harrison Delecki, Marcell Vazquez-Chanlatte, Esen Yel, Kyle Wray 외

Model-based planners for partially observable problems must accommodate both model uncertainty during planning and goal uncertainty during objective inference. However, model-based planners may be brittle under these typ…

Multi-agent learning under uncertainty: Recurrence vs. concentration

2025-12-09 · Kyriakos Lotidis, Panayotis Mertikopoulos, Nicholas Bambos, Jose Blanchet arxiv

In this paper, we examine the convergence landscape of multi-agent learning under uncertainty. Specifically, we analyze two stochastic models of regularized learning in continuous games -- one in continuous and one in di…

Deep Deterministic Uncertainty: A New Simple Baseline

2023-01-01 · CVPR 2023 1 · Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H.S. Torr 외

Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive. We take two complex single-forward-pass unc…

Active LearningSemantic SegmentationUncertainty Quantification

MURO: Deployment Constrained Reinforcement Learning with Model-based Uncertainty Regularized Batch Optimization

2021-09-29 · DiJia Su, Jason D. Lee, John Mulvey, H. Vincent Poor

In many contemporary applications such as healthcare, finance, robotics, and recommendation systems, continuous deployment of new policies for data collection and online learning is either cost ineffective or impractical…

Recommendation Systemsreinforcement-learningReinforcement Learning (RL)Uncertainty Quantification