# UNIT: Unleash Large Language Models Potential for Graph Continual Learning

arXiv: https://arxiv.org/abs/2607.10159 · HTML: https://mlsanity.com/paper/2607.10159/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 11 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs](https://mlsanity.com/paper/2307.03393/) (2023)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks](https://mlsanity.com/paper/2402.07197/) (2024)
- [Efficient Tuning and Inference for Large Language Models on Textual Graphs](https://mlsanity.com/paper/2401.15569/) (2024)
- [Can we Soft Prompt LLMs for Graph Learning Tasks?](https://mlsanity.com/paper/2402.10359/) (2024)
- [Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration](https://mlsanity.com/paper/2312.05229/) (2023)
- [When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learning](https://mlsanity.com/paper/2410.09132/) (2024)
- [Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining](https://mlsanity.com/paper/2403.04780/) (2024)
- [DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning](https://mlsanity.com/paper/2402.13711/) (2024)
- [Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach](https://mlsanity.com/paper/2410.10341/) (2024)
- [Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection](https://mlsanity.com/paper/2507.11997/) (2025)
- [Leveraging Large Language Models for Effective Label-free Node Classification in Text-Attributed Graphs](https://mlsanity.com/paper/2412.11983/) (2024)
- [Can LLMs Alleviate Catastrophic Forgetting in Graph Continual Learning? A Systematic Study](https://mlsanity.com/paper/2505.18697/) (2025)

## Abstract (arXiv)

In real-world multimodal web scenarios, graph-structured data often arrives in a streaming manner, making graph continual learning a crucial paradigm for continuously modeling such evolving structures. However, existing graph continual learning methods still face two fundamental challenges. 1) semantic-structural separation, where the graph-based methods excel at modeling topological relationships but neglect deep semantics. 2) imbalanced knowledge transfer, where existing models fail to effectively leverage general knowledge gained from early tasks to benefit subsequent new tasks. To address above issues, we propose a novel framework, UNleash Large Language Models PotentIal for Graph ConTinual Learning (UNIT). By fine-tuning large language model only on the first task, we bridge the distributional gap between the pre-trained LLM corpus and the target task dataset to enhance the adaptability of LLMs for graph-structured tasks. Meanwhile, we propose an uncertain-aware anchor generation mechanism to effectively preserve representative knowledge across tasks, avoiding the neglect of universal knowledge learned from previous tasks. Additionally, we introduce structural confluence modeling to explicitly integrates graph topology information into semantic information, enhancing the collaborative capabilities between semantic understanding and structural modeling. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance in the graph continual learning task.