# A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm

arXiv: https://arxiv.org/abs/2310.12244 · HTML: https://mlsanity.com/paper/2310.12244/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 85 of its 112 references that are in the map.
- First posted on arXiv 18 Oct 2023.

## Builds on (most cited first, 30 of 85)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)

## Built on by (most cited first, 30 of 33)

- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning](https://mlsanity.com/paper/2410.00911/) (2024)
- [Componential Prompt-Knowledge Alignment for Domain Incremental Learning](https://mlsanity.com/paper/2505.04575/) (2025)
- [Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts](https://mlsanity.com/paper/2507.07100/) (2025)
- [Parameter-Efficient Continual Fine-Tuning: A Survey](https://mlsanity.com/paper/2504.13822/) (2025)
- [E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data](https://mlsanity.com/paper/2404.08814/) (2024)
- [PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization](https://mlsanity.com/paper/2505.12745/) (2025)
- [Continual Hyperbolic Learning of Instances and Classes](https://mlsanity.com/paper/2506.10710/) (2025)
- [Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond](https://mlsanity.com/paper/2408.02983/) (2024)
- [Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees](https://mlsanity.com/paper/2402.02110/) (2024)
- [Pre-trained Recommender Systems: A Causal Debiasing Perspective](https://mlsanity.com/paper/2310.19251/) (2023)
- [Exploring Open-world Continual Learning with Knowns-Unknowns Knowledge Transfer](https://mlsanity.com/paper/2502.20124/) (2025)
- [Information-Theoretic Generalization Bounds of Replay-based Continual Learning](https://mlsanity.com/paper/2507.12043/) (2025)
- [LiteUpdate: A Lightweight Framework for Updating AI-Generated Image Detectors](https://mlsanity.com/paper/2511.07192/) (2025)
- [Towards Domain Adaptive Neural Contextual Bandits](https://mlsanity.com/paper/2406.09564/) (2024)
- [Algorithm Design for Continual Learning in IoT Networks](https://mlsanity.com/paper/2412.16830/) (2024)
- [A Selective Learning Method for Temporal Graph Continual Learning](https://mlsanity.com/paper/2503.01580/) (2025)
- [Stochastic Engrams for Efficient Continual Learning](https://mlsanity.com/paper/2503.21436/) (2025)
- [5G-DIL: Domain Incremental Learning with Similarity-Aware Sampling for Dynamic 5G Indoor Localization](https://mlsanity.com/paper/2505.17684/) (2025)
- [Adaptive Budget Allocation for Orthogonal-Subspace Adapter Tuning in LLMs Continual Learning](https://mlsanity.com/paper/2505.22358/) (2025)
- [Continual Learning of Domain-Invariant Representations](https://mlsanity.com/paper/2605.15775/) (2026)
- [Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2606.05675/) (2026)
- [Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection](https://mlsanity.com/paper/2607.17340/) (2026)
- [Balanced Gradient Sample Retrieval for Enhanced Knowledge Retention in Proxy-based Continual Learning](https://mlsanity.com/paper/2412.14430/) (2024)
- [Towards Macro-AUC oriented Imbalanced Multi-Label Continual Learning](https://mlsanity.com/paper/2412.18231/) (2024)
- [Lifelong Evolution: Collaborative Learning between Large and Small Language Models for Continuous Emergent Fake News Detection](https://mlsanity.com/paper/2506.04739/) (2025)
- [Incremental Human-Object Interaction Detection with Invariant Relation Representation Learning](https://mlsanity.com/paper/2510.27020/) (2025)
- [Real-Time Trend Prediction via Continually-Aligned LLM Query Generation](https://mlsanity.com/paper/2601.17567/) (2026)
- [Server-Proximal Aggregation for Federated Domain-Incremental Learning under Partial Participation: Task-Uniform Convergence and Backward Transfer](https://mlsanity.com/paper/2601.22274/) (2026)
- [HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning](https://mlsanity.com/paper/2605.05776/) (2026)

## Abstract (arXiv)

Domain incremental learning aims to adapt to a sequence of domains with access to only a small subset of data (i.e., memory) from previous domains. Various methods have been proposed for this problem, but it is still unclear how they are related and when practitioners should choose one method over another. In response, we propose a unified framework, dubbed Unified Domain Incremental Learning (UDIL), for domain incremental learning with memory. Our UDIL **unifies** various existing methods, and our theoretical analysis shows that UDIL always achieves a tighter generalization error bound compared to these methods. The key insight is that different existing methods correspond to our bound with different **fixed** coefficients; based on insights from this unification, our UDIL allows **adaptive** coefficients during training, thereby always achieving the tightest bound. Empirical results show that our UDIL outperforms the state-of-the-art domain incremental learning methods on both synthetic and real-world datasets. Code will be available at https://github.com/Wang-ML-Lab/unified-continual-learning.