mlsanityData to 7 Oct 2026

Continual Multimodal Knowledge Graph Construction

arXiv 2305.08698 ↗First posted 15 May 2023cs.CL cs.AI cs.DBcited by 15

Not on the map. Why?

Abstract (arXiv)

Current Multimodal Knowledge Graph Construction (MKGC) models struggle with the real-world dynamism of continuously emerging entities and relations, often succumbing to catastrophic forgetting-loss of previously acquired knowledge. This study introduces benchmarks aimed at fostering the development of the continual MKGC domain. We further introduce MSPT framework, designed to surmount the shortcomings of existing MKGC approaches during multimedia data processing. MSPT harmonizes the retention of learned knowledge (stability) and the integration of new data (plasticity), outperforming current continual learning and multimodal methods. Our results confirm MSPT's superior performance in evolving knowledge environments, showcasing its capacity to navigate balance between stability and plasticity.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 42 of its 77 references that are in the map. First posted on arXiv 15 May 2023.

Builds on

42 of 77 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2016Learning without Forgettingcited by 2,465
  7. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  8. 2016Progressive Neural Networkscited by 1,332
  9. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  10. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  11. 2016Neural Architectures for Named Entity Recognitioncited by 548
  12. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
30 more
  1. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 362
  2. 2019What Makes Training Multi-Modal Classification Networks Hard?cited by 340
  3. 2022Balanced Multimodal Learning via On-the-fly Gradient Modulationcited by 259
  4. 2021KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extractioncited by 180
  5. 2018Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgettingcited by 127
  6. 2019MMKG: Multi-Modal Knowledge Graphscited by 104
  7. 2021Document-level Relation Extraction as Semantic Segmentationcited by 80
  8. 2021Template-free Prompt Tuning for Few-shot NERcited by 73
  9. 2019Sentence Embedding Alignment for Lifelong Relation Extractioncited by 70
  10. 2018Relational recurrent neural networkscited by 65
  11. 2022Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completioncited by 44
  12. 2018Multimodal Named Entity Recognition for Short Social Media Postscited by 43
  13. 2022Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structurecited by 43
  14. 2018Memory-based Parameter Adaptationcited by 35
  15. 2021Curriculum-Meta Learning for Order-Robust Continual Relation Extractioncited by 34
  16. 2022Relational Message Passing for Fully Inductive Knowledge Graph Completioncited by 29
  17. 2021LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Promptingcited by 27
  18. 2022A Survey on Neural Open Information Extraction: Current Status and Future Directionscited by 27
  19. 2020On Modality Bias in the TVQA Datasetcited by 24
  20. 2021ITA: Image-Text Alignments for Multi-Modal Named Entity Recognitioncited by 24
  21. 2022Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularizationcited by 23
  22. 2022Multimodal Analogical Reasoning over Knowledge Graphscited by 21
  23. 2019Aiding Intra-Text Representations with Visual Context for Multimodal Named Entity Recognitioncited by 15
  24. 2022MMKGR: Multi-hop Multi-modal Knowledge Graph Reasoningcited by 13
  25. 2021Time-aware Path Reasoning on Knowledge Graph for Recommendationcited by 11
  26. 2022Towards Relation Extraction From Speechcited by 10
  27. 2022FedKNOW: Federated Continual Learning with Signature Task Knowledge Integration at Edgecited by 10
  28. 2022Flat Multi-modal Interaction Transformer for Named Entity Recognitioncited by 8
  29. 2020Learning Relation Ties with a Force-Directed Graph in Distant Supervised Relation Extractioncited by 3
  30. 2022Syntactic Multi-view Learning for Open Information Extractioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 7; 2026: 3.

15 papers.

Sort:

By area:

  1. 2024Continual Learning for Large Language Models: A Surveycited by 144
  2. 2023LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunitiescited by 97
  3. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  4. 2024Recent Advances of Multimodal Continual Learning: A Comprehensive Surveycited by 39
  5. 2024Continual Learning on Graphs: Challenges, Solutions, and Opportunitiescited by 20
  6. 2025Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoningcited by 19
  7. 2025Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgettingcited by 16
  8. 2024Continual Learning for Smart City: A Surveycited by 9
  9. 2025When Continue Learning Meets Multimodal Large Language Model: A Surveycited by 8
  10. 2025Task-Core Memory Management and Consolidation for Long-term Continual Learningcited by 4
  11. 2026Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptationcited by 4
  12. 2026CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuningcited by 3
3 more
  1. 2025DiffusionCom: Structure-Aware Multimodal Diffusion Model for Multimodal Knowledge Graph Completioncited by 1
  2. 2025CMIP-CIL: A Cross-Modal Benchmark for Image-Point Class Incremental Learningcited by 0
  3. 2026Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Eracited by 0