# Componential Prompt-Knowledge Alignment for Domain Incremental Learning

arXiv: https://arxiv.org/abs/2505.04575 · HTML: https://mlsanity.com/paper/2505.04575/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 49 references that are in the map.
- First posted on arXiv 7 May 2025.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning](https://mlsanity.com/paper/2207.12819/) (2022)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [MMA-Diffusion: MultiModal Attack on Diffusion Models](https://mlsanity.com/paper/2311.17516/) (2023)
- [Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need](https://mlsanity.com/paper/2303.07338/) (2023)
- [Self-Supervised Models are Continual Learners](https://mlsanity.com/paper/2112.04215/) (2021)
- [Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2105.15075/) (2021)
- [Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality](https://mlsanity.com/paper/2310.07234/) (2023)
- [Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations](https://mlsanity.com/paper/1807.01697/) (2018)
- [Person Re-identification Method Based on Color Attack and Joint Defence](https://mlsanity.com/paper/2111.09571/) (2021)
- [An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions](https://mlsanity.com/paper/2204.08817/) (2022)
- [Consistent Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2403.08568/) (2024)
- [Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference](https://mlsanity.com/paper/2211.15969/) (2022)
- [Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2306.14451/) (2023)
- [Vision Transformers with Mixed-Resolution Tokenization](https://mlsanity.com/paper/2304.00287/) (2023)
- [Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning](https://mlsanity.com/paper/2303.14771/) (2023)
- [A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm](https://mlsanity.com/paper/2310.12244/) (2023)
- [General Incremental Learning with Domain-aware Categorical Representations](https://mlsanity.com/paper/2204.04078/) (2022)
- [Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching](https://mlsanity.com/paper/2407.05005/) (2024)
- [In Defense of the Learning Without Forgetting for Task Incremental Learning](https://mlsanity.com/paper/2107.12304/) (2021)
- [Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2402.19026/) (2024)
- [STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding](https://mlsanity.com/paper/2503.15973/) (2025)
- [SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting](https://mlsanity.com/paper/2503.12866/) (2025)

## Built on by (most cited first, 13 of 13)

- [Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification](https://mlsanity.com/paper/2507.01884/) (2025)
- [Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation](https://mlsanity.com/paper/2510.12150/) (2025)
- [C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning](https://mlsanity.com/paper/2509.19674/) (2025)
- [State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding](https://mlsanity.com/paper/2510.12160/) (2025)
- [Continual Knowledge Consolidation LORA for Domain Incremental Learning](https://mlsanity.com/paper/2510.16077/) (2025)
- [InTAct: Interval-based Task Activation Consolidation for Continual Learning](https://mlsanity.com/paper/2511.17439/) (2025)
- [Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identification](https://mlsanity.com/paper/2603.19678/) (2026)
- [RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation](https://mlsanity.com/paper/2603.24295/) (2026)
- [STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detection](https://mlsanity.com/paper/2605.20738/) (2026)
- [UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis](https://mlsanity.com/paper/2507.18997/) (2025)
- [Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection](https://mlsanity.com/paper/2512.19022/) (2025)
- [Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction Tuning](https://mlsanity.com/paper/2609.13742/) (2026)
- [Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection](https://mlsanity.com/paper/2609.37586/) (2026)

## Abstract (arXiv)

Domain Incremental Learning (DIL) aims to learn from non-stationary data streams across domains while retaining and utilizing past knowledge. Although prompt-based methods effectively store multi-domain knowledge in prompt parameters and obtain advanced performance through cross-domain prompt fusion, we reveal an intrinsic limitation: component-wise misalignment between domain-specific prompts leads to conflicting knowledge integration and degraded predictions. This arises from the random positioning of knowledge components within prompts, where irrelevant component fusion introduces interference.To address this, we propose Componential Prompt-Knowledge Alignment (KA-Prompt), a novel prompt-based DIL method that introduces component-aware prompt-knowledge alignment during training, significantly improving both the learning and inference capacity of the model. KA-Prompt operates in two phases: (1) Initial Componential Structure Configuring, where a set of old prompts containing knowledge relevant to the new domain are mined via greedy search, which is then exploited to initialize new prompts to achieve reusable knowledge transfer and establish intrinsic alignment between new and old prompts. (2) Online Alignment Preservation, which dynamically identifies the target old prompts and applies adaptive componential consistency constraints as new prompts evolve. Extensive experiments on DIL benchmarks demonstrate the effectiveness of our KA-Prompt. Our source code is available at https://github.com/zhoujiahuan1991/ICML2025-KA-Prompt