# Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting

arXiv: https://arxiv.org/abs/2010.01528 · HTML: https://mlsanity.com/paper/2010.01528/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2020.

## Built on by (most cited first, 30 of 34)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies](https://mlsanity.com/paper/2407.19354/) (2024)
- [BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief](https://mlsanity.com/paper/2109.14723/) (2021)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [PIVOT: Prompting for Video Continual Learning](https://mlsanity.com/paper/2212.04842/) (2022)
- [On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning](https://mlsanity.com/paper/2210.06443/) (2022)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Continual Learning via Bit-Level Information Preserving](https://mlsanity.com/paper/2105.04444/) (2021)
- [On Guiding Visual Attention with Language Specification](https://mlsanity.com/paper/2202.08926/) (2022)
- [Optimizing Reusable Knowledge for Continual Learning via Metalearning](https://mlsanity.com/paper/2106.05390/) (2021)
- [BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning](https://mlsanity.com/paper/2305.04769/) (2023)
- [Use-Case-Grounded Simulations for Explanation Evaluation](https://mlsanity.com/paper/2206.02256/) (2022)
- [Sparse Coding in a Dual Memory System for Lifelong Learning](https://mlsanity.com/paper/2301.05058/) (2022)
- [Saliency Guided Experience Packing for Replay in Continual Learning](https://mlsanity.com/paper/2109.04954/) (2021)
- [Task Agnostic Representation Consolidation: a Self-supervised based Continual Learning Approach](https://mlsanity.com/paper/2207.06267/) (2022)
- [Anti-Retroactive Interference for Lifelong Learning](https://mlsanity.com/paper/2208.12967/) (2022)
- [D3Former: Debiased Dual Distilled Transformer for Incremental Learning](https://mlsanity.com/paper/2208.00777/) (2022)
- [Continual Learning for Predictive Maintenance: Overview and Challenges](https://mlsanity.com/paper/2301.12467/) (2023)
- [Memory Population in Continual Learning via Outlier Elimination](https://mlsanity.com/paper/2207.01145/) (2022)
- [Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection](https://mlsanity.com/paper/2209.09839/) (2022)
- [Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning](https://mlsanity.com/paper/2212.08251/) (2022)
- [Latent Spectral Regularization for Continual Learning](https://mlsanity.com/paper/2301.03345/) (2023)
- [Saliency-Guided Hidden Associative Replay for Continual Learning](https://mlsanity.com/paper/2310.04334/) (2023)
- [CEAT: Continual Expansion and Absorption Transformer for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2403.06670/) (2024)
- [Saliency-Augmented Memory Completion for Continual Learning](https://mlsanity.com/paper/2212.13242/) (2022)
- [A Protocol for Continual Explanation of SHAP](https://mlsanity.com/paper/2306.07218/) (2023)
- [Selective Attention-based Modulation for Continual Learning](https://mlsanity.com/paper/2403.20086/) (2024)
- [Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments](https://mlsanity.com/paper/2407.08279/) (2024)
- [Continual Learning for Multimodal Data Fusion of a Soft Gripper](https://mlsanity.com/paper/2409.13792/) (2024)
- [CIP-Net: Continual Interpretable Prototype-based Network](https://mlsanity.com/paper/2512.07981/) (2025)

## Abstract (arXiv)

The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory in the form of a replay buffer can reduce performance degradation on prior tasks. We hypothesize that forgetting can be further reduced when the model is encouraged to remember the textitevidence for previously made decisions. As a first step towards exploring this hypothesis, we propose a simple novel training paradigm, called Remembering for the Right Reasons (RRR), that additionally stores visual model explanations for each example in the buffer and ensures the model has "the right reasons" for its predictions by encouraging its explanations to remain consistent with those used to make decisions at training time. Without this constraint, there is a drift in explanations and increase in forgetting as conventional continual learning algorithms learn new tasks. We demonstrate how RRR can be easily added to any memory or regularization-based approach and results in reduced forgetting, and more importantly, improved model explanations. We have evaluated our approach in the standard and few-shot settings and observed a consistent improvement across various CL approaches using different architectures and techniques to generate model explanations and demonstrated our approach showing a promising connection between explainability and continual learning. Our code is available at urlhttps://github.com/SaynaEbrahimi/Remembering-for-the-Right-Reasons.