# ETT-CKGE: Efficient Task-driven Tokens for Continual Knowledge Graph Embedding

arXiv: https://arxiv.org/abs/2506.08158 · HTML: https://mlsanity.com/paper/2506.08158/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [LinkBERT: Pretraining Language Models with Document Links](https://mlsanity.com/paper/2203.15827/) (2022)
- [SimplE Embedding for Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/1802.04868/) (2018)
- [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://mlsanity.com/paper/2302.08043/) (2023)
- [Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting](https://mlsanity.com/paper/1802.02950/) (2018)
- [A Comprehensive Survey on Deep Graph Representation Learning](https://mlsanity.com/paper/2304.05055/) (2023)
- [Sentence Embedding Alignment for Lifelong Relation Extraction](https://mlsanity.com/paper/1903.02588/) (2019)
- [Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding](https://mlsanity.com/paper/1811.01399/) (2018)
- [Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs](https://mlsanity.com/paper/2211.15845/) (2022)
- [Continual Learning on Graphs: Challenges, Solutions, and Opportunities](https://mlsanity.com/paper/2402.11565/) (2024)
- [Towards Continual Knowledge Graph Embedding via Incremental Distillation](https://mlsanity.com/paper/2405.04453/) (2024)
- [Fast and Continual Knowledge Graph Embedding via Incremental LoRA](https://mlsanity.com/paper/2407.05705/) (2024)
- [HGTDP-DTA: Hybrid Graph-Transformer with Dynamic Prompt for Drug-Target Binding Affinity Prediction](https://mlsanity.com/paper/2406.17697/) (2024)
- [KGIF: Optimizing Relation-Aware Recommendations with Knowledge Graph Information Fusion](https://mlsanity.com/paper/2501.04161/) (2025)

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

- [MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution](https://mlsanity.com/paper/2604.26283/) (2026)

## Abstract (arXiv)

Continual Knowledge Graph Embedding (CKGE) seeks to integrate new knowledge while preserving past information. However, existing methods struggle with efficiency and scalability due to two key limitations: (1) suboptimal knowledge preservation between snapshots caused by manually designed node/relation importance scores that ignore graph dependencies relevant to the downstream task, and (2) computationally expensive graph traversal for node/relation importance calculation, leading to slow training and high memory overhead. To address these limitations, we introduce ETT-CKGE (Efficient, Task-driven, Tokens for Continual Knowledge Graph Embedding), a novel task-guided CKGE method that leverages efficient task-driven tokens for efficient and effective knowledge transfer between snapshots. Our method introduces a set of learnable tokens that directly capture task-relevant signals, eliminating the need for explicit node scoring or traversal. These tokens serve as consistent and reusable guidance across snapshots, enabling efficient token-masked embedding alignment between snapshots. Importantly, knowledge transfer is achieved through simple matrix operations, significantly reducing training time and memory usage. Extensive experiments across six benchmark datasets demonstrate that ETT-CKGE consistently achieves superior or competitive predictive performance, while substantially improving training efficiency and scalability compared to state-of-the-art CKGE methods. The code is available at: https://github.com/lijingzhu1/ETT-CKGE/tree/main