# Forward and Backward Knowledge Transfer for Sentiment Classification

arXiv: https://arxiv.org/abs/1906.03506 · HTML: https://mlsanity.com/paper/1906.03506/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2019.

## Built on by (most cited first, 9 of 9)

- [Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning](https://mlsanity.com/paper/2112.02706/) (2021)
- [Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks](https://mlsanity.com/paper/2112.10017/) (2021)
- [Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks](https://mlsanity.com/paper/2112.03271/) (2021)
- [CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks](https://mlsanity.com/paper/2112.02714/) (2021)
- [Learning to Prompt Knowledge Transfer for Open-World Continual Learning](https://mlsanity.com/paper/2312.14990/) (2023)
- [Continual Learning with Knowledge Transfer for Sentiment Classification](https://mlsanity.com/paper/2112.10021/) (2021)
- [Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning](https://mlsanity.com/paper/2207.05742/) (2022)
- [Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Grouping](https://mlsanity.com/paper/2502.20032/) (2025)
- [HOP to the Next Tasks and Domains for Continual Learning in NLP](https://mlsanity.com/paper/2402.18449/) (2024)

## Abstract (arXiv)

This paper studies the problem of learning a sequence of sentiment classification tasks. The learned knowledge from each task is retained and used to help future or subsequent task learning. This learning paradigm is called Lifelong Learning (LL). However, existing LL methods either only transfer knowledge forward to help future learning and do not go back to improve the model of a previous task or require the training data of the previous task to retrain its model to exploit backward/reverse knowledge transfer. This paper studies reverse knowledge transfer of LL in the context of naive Bayesian (NB) classification. It aims to improve the model of a previous task by leveraging future knowledge without retraining using its training data. This is done by exploiting a key characteristic of the generative model of NB. That is, it is possible to improve the NB classifier for a task by improving its model parameters directly by using the retained knowledge from other tasks. Experimental results show that the proposed method markedly outperforms existing LL baselines.