# Energy-Based Models for Continual Learning

arXiv: https://arxiv.org/abs/2011.12216 · HTML: https://mlsanity.com/paper/2011.12216/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 30 of 32)

- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [The CLEAR Benchmark: Continual LEArning on Real-World Imagery](https://mlsanity.com/paper/2201.06289/) (2022)
- [Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts](https://mlsanity.com/paper/2305.19951/) (2023)
- [Posterior Meta-Replay for Continual Learning](https://mlsanity.com/paper/2103.01133/) (2021)
- [Class-Incremental Learning with Generative Classifiers](https://mlsanity.com/paper/2104.10093/) (2021)
- [Energy-based Latent Aligner for Incremental Learning](https://mlsanity.com/paper/2203.14952/) (2022)
- [Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations](https://mlsanity.com/paper/2401.14142/) (2024)
- [Learning Iterative Reasoning through Energy Minimization](https://mlsanity.com/paper/2206.15448/) (2022)
- [Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2303.09447/) (2023)
- [Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning](https://mlsanity.com/paper/2309.06086/) (2023)
- [Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions](https://mlsanity.com/paper/2211.00568/) (2022)
- [Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings](https://mlsanity.com/paper/2410.20768/) (2024)
- [Autoencoder-Based Hybrid Replay for Class-Incremental Learning](https://mlsanity.com/paper/2505.05926/) (2025)
- [Energy-Based Models for Cross-Modal Localization using Convolutional Transformers](https://mlsanity.com/paper/2306.04021/) (2023)
- [Closed-Loop Transformers: Autoregressive Modeling as Iterative Latent Equilibrium](https://mlsanity.com/paper/2511.21882/) (2025)
- [Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers](https://mlsanity.com/paper/2201.01488/) (2022)
- [Saliency-Augmented Memory Completion for Continual Learning](https://mlsanity.com/paper/2212.13242/) (2022)
- [LSEBMCL: A Latent Space Energy-Based Model for Continual Learning](https://mlsanity.com/paper/2501.05495/) (2025)
- [Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data](https://mlsanity.com/paper/2108.04227/) (2021)
- [Particle Dynamics for Learning EBMs](https://mlsanity.com/paper/2111.13772/) (2021)
- [DIRA: Dynamic Domain Incremental Regularised Adaptation](https://mlsanity.com/paper/2205.00147/) (2022)
- [Diagnosing Catastrophe: Large parts of accuracy loss in continual learning can be accounted for by readout misalignment](https://mlsanity.com/paper/2310.05644/) (2023)
- [Stochastic Engrams for Efficient Continual Learning](https://mlsanity.com/paper/2503.21436/) (2025)
- [SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2604.02222/) (2026)
- [EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering](https://mlsanity.com/paper/2206.14355/) (2022)
- [Changes from Classical Statistics to Modern Statistics and Data Science](https://mlsanity.com/paper/2211.03756/) (2022)
- [On Feature Diversity in Energy-based Models](https://mlsanity.com/paper/2306.01489/) (2023)
- [LIME-Eval: Rethinking Low-light Image Enhancement Evaluation via Object Detection](https://mlsanity.com/paper/2410.08810/) (2024)
- [PPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning](https://mlsanity.com/paper/2512.15658/) (2025)

## Abstract (arXiv)

We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs change the underlying training objective to cause less interference with previously learned information. Our proposed version of EBMs for continual learning is simple, efficient, and outperforms baseline methods by a large margin on several benchmarks. Moreover, our proposed contrastive divergence-based training objective can be combined with other continual learning methods, resulting in substantial boosts in their performance. We further show that EBMs are adaptable to a more general continual learning setting where the data distribution changes without the notion of explicitly delineated tasks. These observations point towards EBMs as a useful building block for future continual learning methods.