# Forward-Only Continual Learning

arXiv: https://arxiv.org/abs/2509.01533 · HTML: https://mlsanity.com/paper/2509.01533/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 54 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 29 of 29)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Fine-Tuning Language Models with Just Forward Passes](https://mlsanity.com/paper/2305.17333/) (2023)
- [The Forward-Forward Algorithm: Some Preliminary Investigations](https://mlsanity.com/paper/2212.13345/) (2022)
- [Black-Box Tuning for Language-Model-as-a-Service](https://mlsanity.com/paper/2201.03514/) (2022)
- [Understanding the Role of Training Regimes in Continual Learning](https://mlsanity.com/paper/2006.06958/) (2020)
- [RanPAC: Random Projections and Pre-trained Models for Continual Learning](https://mlsanity.com/paper/2307.02251/) (2023)
- [Continual Learning with Pre-Trained Models: A Survey](https://mlsanity.com/paper/2401.16386/) (2024)
- [Continual Pre-Training Mitigates Forgetting in Language and Vision](https://mlsanity.com/paper/2205.09357/) (2022)
- [The HSIC Bottleneck: Deep Learning without Back-Propagation](https://mlsanity.com/paper/1908.01580/) (2019)
- [Test-Time Model Adaptation with Only Forward Passes](https://mlsanity.com/paper/2404.01650/) (2024)
- [PILOT: A Pre-Trained Model-Based Continual Learning Toolbox](https://mlsanity.com/paper/2309.07117/) (2023)
- [Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks](https://mlsanity.com/paper/2410.04055/) (2024)
- [Continual Forgetting for Pre-trained Vision Models](https://mlsanity.com/paper/2403.11530/) (2024)
- [DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2403.17503/) (2024)
- [Generative Multi-modal Models are Good Class-Incremental Learners](https://mlsanity.com/paper/2403.18383/) (2024)
- [Advancing Prompt-Based Methods for Replay-Independent General Continual Learning](https://mlsanity.com/paper/2503.00677/) (2025)
- [Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single](https://mlsanity.com/paper/2304.11153/) (2023)
- [Continual Learning with Diffusion-based Generative Replay for Industrial Streaming Data](https://mlsanity.com/paper/2406.15766/) (2024)
- [Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks](https://mlsanity.com/paper/2403.09377/) (2024)
- [IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse](https://mlsanity.com/paper/2308.07351/) (2023)

## Built on by (most cited first, 1 of 1)

- [Why Zeroth-Order Adaptation May Forget Less: A Randomized Shaping Theory](https://mlsanity.com/paper/2605.10658/) (2026)

## Abstract (arXiv)

Catastrophic forgetting remains a central challenge in continual learning (CL) with pre-trained models. While existing approaches typically freeze the backbone and fine-tune a small number of parameters to mitigate forgetting, they still rely on iterative error backpropagation and gradient-based optimization, which can be computationally intensive and less suitable for resource-constrained environments. To address this, we propose FoRo, a forward-only, gradient-free continual learning method. FoRo consists of a lightweight prompt tuning strategy and a novel knowledge encoding mechanism, both designed without modifying the pre-trained model. Specifically, prompt embeddings are inserted at the input layer and optimized using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), which mitigates distribution shifts and extracts high-quality task representations. Subsequently, task-specific knowledge is encoded into a knowledge encoding matrix via nonlinear random projection and recursive least squares, enabling incremental updates to the classifier without revisiting prior data. Experiments show that FoRo significantly reduces average forgetting and improves accuracy. Thanks to forward-only learning, FoRo reduces memory usage and run time while maintaining high knowledge retention across long task sequences. These results suggest that FoRo could serve as a promising direction for exploring continual learning with pre-trained models, especially in real-world multimedia applications where both efficiency and effectiveness are critical.