# When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs

arXiv: https://arxiv.org/abs/2604.02778 · HTML: https://mlsanity.com/paper/2604.02778/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 56 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://mlsanity.com/paper/1901.09590/) (2019)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [MMKG: Multi-Modal Knowledge Graphs](https://mlsanity.com/paper/1903.05485/) (2019)
- [Multi-Modal Knowledge Graph Construction and Application: A Survey](https://mlsanity.com/paper/2202.05786/) (2022)
- [Sentence Embedding Alignment for Lifelong Relation Extraction](https://mlsanity.com/paper/1903.02588/) (2019)
- [Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey](https://mlsanity.com/paper/2402.05391/) (2024)
- [Multimodal Reasoning with Multimodal Knowledge Graph](https://mlsanity.com/paper/2406.02030/) (2024)
- [Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs](https://mlsanity.com/paper/2211.15845/) (2022)
- [IMF: Interactive Multimodal Fusion Model for Link Prediction](https://mlsanity.com/paper/2303.10816/) (2023)
- [Disentangle-based Continual Graph Representation Learning](https://mlsanity.com/paper/2010.02565/) (2020)
- [NativE: Multi-modal Knowledge Graph Completion in the Wild](https://mlsanity.com/paper/2406.17605/) (2024)
- [Towards Continual Knowledge Graph Embedding via Incremental Distillation](https://mlsanity.com/paper/2405.04453/) (2024)
- [Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation](https://mlsanity.com/paper/2404.09468/) (2024)
- [Fast and Continual Knowledge Graph Embedding via Incremental LoRA](https://mlsanity.com/paper/2407.05705/) (2024)
- [Rethinking Regularization Methods for Knowledge Graph Completion](https://mlsanity.com/paper/2505.23442/) (2025)
- [KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking](https://mlsanity.com/paper/2504.15135/) (2025)
- [Learning to Evolve: Bayesian-Guided Continual Knowledge Graph Embedding](https://mlsanity.com/paper/2508.02426/) (2025)
- [Dark Side of Modalities: Reinforced Multimodal Distillation for Multimodal Knowledge Graph Reasoning](https://mlsanity.com/paper/2507.20738/) (2025)

## Built on by (most cited first, 2 of 2)

- [CMKL: Modality-Aware Continual Learning for Evolving Biomedical Knowledge Graphs](https://mlsanity.com/paper/2605.10510/) (2026)
- [PrimeKG-CL: A Continual Graph Learning Benchmark on Evolving Biomedical Knowledge Graphs](https://mlsanity.com/paper/2605.10529/) (2026)

## Abstract (arXiv)

Real-world multimodal knowledge graphs (MMKGs) are dynamic, with new entities, relations, and multimodal knowledge emerging over time. Existing continual knowledge graph reasoning (CKGR) methods focus on structural triples and cannot fully exploit multimodal signals from new entities. Existing multimodal knowledge graph reasoning (MMKGR) methods, however, usually assume static graphs and suffer catastrophic forgetting as graphs evolve. To address this gap, we present a systematic study of continual multimodal knowledge graph reasoning (CMMKGR). We construct several continual multimodal knowledge graph benchmarks from existing MMKG datasets and propose MRCKG, a new CMMKGR model. Specifically, MRCKG employs a multimodal-structural collaborative curriculum to schedule progressive learning based on the structural connectivity of new triples to the historical graph and their multimodal compatibility. It also introduces a cross-modal knowledge preservation mechanism to mitigate forgetting through entity representation stability, relational semantic consistency, and modality anchoring. In addition, a multimodal contrastive replay scheme with a two-stage optimization strategy reinforces learned knowledge via multimodal importance sampling and representation alignment. Experiments on multiple datasets show that MRCKG preserves previously learned multimodal knowledge while substantially improving the learning of new knowledge.