arXiv Machine Learning October 16, 2026 By Guiquan Sun, Xikun Zhang, Jingchao Ni, Dongjin Song

HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learning

Read the original on arXiv Machine Learning →

HERO is a heterogeneous continual graph learning framework that preserves historical knowledge at both structural and semantic levels while adapting to new tasks. It uses DiSCo to select representative target nodes and reconstruct compact heterogeneous contexts, and applies multi-level knowledge distillation to align task-conditioned predictions with semantic responses. Experiments on four datasets with three HGNN backbones show HERO achieves best or tied-best average performance while maintaining competitive forgetting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 14

UNIT: Unleash Large Language Models Potential for Graph Continual Learning

arXiv:2607. 10159v1 Announce Type: new Abstract: 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.

By Tairan Huang, Yili Wang, Beibei Hu, Yiting Shi, Qiutong Li, Changlong He, Jianliang Gao

llms fine-tuning multimodal benchmarks

arXiv Machine Learning

Jun 2

G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs

arXiv:2606. 01873v1 Announce Type: new Abstract: LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning.

By Yuhan Wang, Yibo Ding, Yutong Ye, Mufan Zhao, Wenbo Zhang, Ruijie Wang, Jianxin Li

llms rag fine-tuning multimodal benchmarks safety

arXiv AI

Sep 30

HiTS-CL: A Continual Learning Framework for Long-Horizon Temporal Knowledge Graph Extrapolation

arXiv:2609.36559v1 Announce Type: cross Abstract: Extrapolative temporal knowledge graph reasoning (TKGR) predicts future facts from historical snapshots. Most existing methods train once on an early...

By Yansong Liu, Rui Liu, Yuan Zuo, Hongwei Zhao, Da Fu, Fuwei Zhang, Fuzhen Zhuang, Yong Chen, Zhe Li

fine-tuning efficiency benchmarks

arXiv AI

Aug 7

CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning

arXiv:2605. 20247v2 Announce Type: replace-cross Abstract: Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs).

By Yang Liu, Toan Nguyen, Flora D. Salim

llms fine-tuning multimodal benchmarks safety

arXiv AI

Sep 7

MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning

MePo++ is a post‑training framework designed for general continual learning (GCL) that unifies representation refinement and reconciliation. It introduces MetaPrep, which enhances representation plasticity via unsupervised meta‑refinement on pseudo continual sequences, and StreamAlign, which maintains stability by reconciling online features with a stable pretrained geometry. Experiments across various pretrained models, datasets, and continual learning baselines show that MePo++ consistently improves performance in PTM‑based GCL.

By Guanglong Sun, Kanglei Zhou, Liyuan Wang, Qi Cheng, Hongwei Yan, Shuang Cui, Hang Su, Jun Zhu, Yi Zhong

safety

arXiv Machine Learning

Oct 15

MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning

arXiv:2610.20238v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) excel on graph-structured data but suffer catastrophic forgetting when classes arrive sequentially. In class-incremental g...

By Junlin Chen, Wenhao Wang, Junchao Xu, Qingsong Yao, Fei Xue, Li Sun, Xiao Wang, Ruijie Wang

fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

UNIT: Unleash Large Language Models Potential for Graph Continual Learning

G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs

HiTS-CL: A Continual Learning Framework for Long-Horizon Temporal Knowledge Graph Extrapolation

CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning

MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning

MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning