# Exploring Example Influence in Continual Learning

arXiv: https://arxiv.org/abs/2209.12241 · HTML: https://mlsanity.com/paper/2209.12241/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 25 Sep 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [Optimizing Millions of Hyperparameters by Implicit Differentiation](https://mlsanity.com/paper/1911.02590/) (2019)
- [Using Hindsight to Anchor Past Knowledge in Continual Learning](https://mlsanity.com/paper/2002.08165/) (2020)
- [Rethinking Experience Replay: a Bag of Tricks for Continual Learning](https://mlsanity.com/paper/2010.05595/) (2020)
- [Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters](https://mlsanity.com/paper/1511.06727/) (2015)
- [Gradient-based Editing of Memory Examples for Online Task-free Continual Learning](https://mlsanity.com/paper/2006.15294/) (2020)
- [An Investigation of Replay-based Approaches for Continual Learning](https://mlsanity.com/paper/2108.06758/) (2021)
- [Multi-Domain Multi-Task Rehearsal for Lifelong Learning](https://mlsanity.com/paper/2012.07236/) (2020)
- [Data Dropout: Optimizing Training Data for Convolutional Neural Networks](https://mlsanity.com/paper/1809.00193/) (2018)
- [AGCN: Augmented Graph Convolutional Network for Lifelong Multi-label Image Recognition](https://mlsanity.com/paper/2203.05534/) (2022)
- [Improved Schemes for Episodic Memory-based Lifelong Learning](https://mlsanity.com/paper/1909.11763/) (2019)
- [Class-Incremental Lifelong Learning in Multi-Label Classification](https://mlsanity.com/paper/2207.07840/) (2022)

## Built on by (most cited first, 30 of 44)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [Learning without Forgetting for Vision-Language Models](https://mlsanity.com/paper/2305.19270/) (2023)
- [PILOT: A Pre-Trained Model-Based Continual Learning Toolbox](https://mlsanity.com/paper/2309.07117/) (2023)
- [Regularizing Second-Order Influences for Continual Learning](https://mlsanity.com/paper/2304.10177/) (2023)
- [Multi-Label Continual Learning using Augmented Graph Convolutional Network](https://mlsanity.com/paper/2211.14763/) (2022)
- [Never-Ending Behavior-Cloning Agent for Robotic Manipulation](https://mlsanity.com/paper/2403.00336/) (2024)
- [SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting](https://mlsanity.com/paper/2505.22370/) (2025)
- [Continuous Subspace Optimization for Continual Learning](https://mlsanity.com/paper/2505.11816/) (2025)
- [Improving Replay Sample Selection and Storage for Less Forgetting in Continual Learning](https://mlsanity.com/paper/2308.01895/) (2023)
- [Variational Continual Test-Time Adaptation](https://mlsanity.com/paper/2402.08182/) (2024)
- [Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning](https://mlsanity.com/paper/2505.22389/) (2025)
- [Confidence Self-Calibration for Multi-Label Class-Incremental Learning](https://mlsanity.com/paper/2403.12559/) (2024)
- [Dynamically Anchored Prompting for Task-Imbalanced Continual Learning](https://mlsanity.com/paper/2404.14721/) (2024)
- [Controllable Continual Test-Time Adaptation](https://mlsanity.com/paper/2405.14602/) (2024)
- [Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation](https://mlsanity.com/paper/2503.22136/) (2025)
- [Centroid Distance Distillation for Effective Rehearsal in Continual Learning](https://mlsanity.com/paper/2303.02954/) (2023)
- [Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration](https://mlsanity.com/paper/2403.11373/) (2024)
- [Integral Continual Learning Along the Tangent Vector Field of Tasks](https://mlsanity.com/paper/2211.13108/) (2022)
- [OpenGCD: Assisting Open World Recognition with Generalized Category Discovery](https://mlsanity.com/paper/2308.06926/) (2023)
- [Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System](https://mlsanity.com/paper/2405.10992/) (2024)
- [Test-Time Discovery via Hashing Memory](https://mlsanity.com/paper/2503.10699/) (2025)
- [Understanding Data Influence with Differential Approximation](https://mlsanity.com/paper/2508.14648/) (2025)
- [Lifelong Embodied Navigation Learning](https://mlsanity.com/paper/2603.06073/) (2026)
- [Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2310.20268/) (2023)
- [BSDP: Brain-inspired Streaming Dual-level Perturbations for Online Open World Object Detection](https://mlsanity.com/paper/2403.02637/) (2024)
- [Lifelong Event Detection with Embedding Space Separation and Compaction](https://mlsanity.com/paper/2404.02507/) (2024)
- [Overcoming Domain Drift in Online Continual Learning](https://mlsanity.com/paper/2405.09133/) (2024)
- [Improving Data-aware and Parameter-aware Robustness for Continual Learning](https://mlsanity.com/paper/2405.17054/) (2024)
- [Rebalancing Multi-Label Class-Incremental Learning](https://mlsanity.com/paper/2408.12161/) (2024)

## Abstract (arXiv)

Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks). Due to the fact that past training data is not available, it is valuable to explore the influence difference on S and P among training examples, which may improve the learning pattern towards better SP. Inspired by Influence Function (IF), we first study example influence via adding perturbation to example weight and computing the influence derivation. To avoid the storage and calculation burden of Hessian inverse in neural networks, we propose a simple yet effective MetaSP algorithm to simulate the two key steps in the computation of IF and obtain the S- and P-aware example influence. Moreover, we propose to fuse two kinds of example influence by solving a dual-objective optimization problem, and obtain a fused influence towards SP Pareto optimality. The fused influence can be used to control the update of model and optimize the storage of rehearsal. Empirical results show that our algorithm significantly outperforms state-of-the-art methods on both task- and class-incremental benchmark CL datasets.