paper-with-me

Papers

Continual Learning for Text Classification with Information Disentanglement Based Regularization

2021-04-12 · NAACL 2021 4 · Yufan Huang, Yanzhe Zhang, Jiaao Chen, Xuezhi Wang, Diyi Yang

Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous tasks, without much emphasis on how to well generalize models to new tasks. In this work, we propose an information disentanglement based regularization method for continual learning on text classification. Our proposed method first disentangles text hidden spaces into representations that are generic to all tasks and representations specific to each individual task, and further regularizes these representations differently to better constrain the knowledge required to generalize. We also introduce two simple auxiliary tasks: next sentence prediction and task-id prediction, for learning better generic and specific representation spaces. Experiments conducted on large-scale benchmarks demonstrate the effectiveness of our method in continual text classification tasks with various sequences and lengths over state-of-the-art baselines. We have publicly released our code at https://github.com/GT-SALT/IDBR.

📄 PDF Abstract BibTeX arXiv:2104.05489

Code (1)

GT-SALT/IDBR 공식 구현 pytorch

Tasks

Continual LearningDisentanglementGeneral ClassificationSentencetext-classificationText Classification

Similar Papers 제목 키워드 기반

Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization

2023-12-27 · Sebastian Dziadzio, Çağatay Yıldız, Gido M. van de Ven, Tomasz Trzciński 외

The ability of machine learning systems to learn continually is hindered by catastrophic forgetting, the tendency of neural networks to overwrite previously acquired knowledge when learning a new task. Existing methods m…

ClassificationContinual LearningDisentanglementMemorization+1

Disentanglement of Color and Shape Representations for Continual Learning

2020-07-13 · David Berga, Marc Masana, Joost Van de Weijer

We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture. We tested …

Continual LearningDisentanglement

ConDiSR: Contrastive Disentanglement and Style Regularization for Single Domain Generalization

2024-03-14 · Aleksandr Matsun, Numan Saeed, Fadillah Adamsyah Maani, Mohammad Yaqub

Medical data often exhibits distribution shifts, which cause test-time performance degradation for deep learning models trained using standard supervised learning pipelines. This challenge is addressed in the field of Do…

ClassificationDisentanglementDomain Generalizationimage-classification+2

Text Classification and Clustering with Annealing Soft Nearest Neighbor Loss

2021-07-23 · Abien Fred Agarap

We define disentanglement as how far class-different data points from each other are, relative to the distances among class-similar data points. When maximizing disentanglement during representation learning, we obtain a…

ClassificationClusteringDisentanglementRepresentation Learning+3

Continual Distributed Learning for Crisis Management

2021-04-26 · Aman Priyanshu, Mudit Sinha, Shreyans Mehta

Social media platforms such as Twitter, Facebook etc can be utilised as an important source of information during disaster events. This information can be used for disaster response and crisis management if processed acc…

Continual LearningDisaster ResponseFederated LearningManagement+2