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.
By Guiquan Sun, Xikun Zhang, Jingchao Ni, Dongjin Song
The paper introduces Router Drift Control (RDC), a method for mitigating off‑policy degradation in Mixture‑of‑Experts reinforcement learning. RDC uses the disagreement between rollout and training routers to detect stale routing decisions and selectively rejects high‑drift responses, thereby avoiding the gradient bias introduced by Rollout Routing Replay (R3). Experiments show that RDC improves validation accuracy, especially in asynchronous training settings, outperforming both R3 and Truncated Importance Sampling (TIS).
By Liangyao Jin, Zhixin Wang, Liming Liu, Mingjun Zhang, Zhengzhou Zhu, Fangcheng Fu, Jinlong Hou, Yuan Cheng, Xiaohe Hu, Ping Zhang, Siyuan Feng
arXiv:2609.25781v1 Announce Type: new
Abstract: Graph Incremental Learning has garnered increasing attention as dynamic graph data continues to emerge across diverse fields. Conventional approaches p...
By Zihan Mei, Zhili Qin, Tongze Zhang, Hongyuan Liu, Junming Shao, Qinli Yang
arXiv:2608. 01252v1 Announce Type: new Abstract: Catastrophic forgetting is a major problem in task-incremental learning, where neural networks tend to overwrite previously learned knowledge when trained on new tasks.
By Pengxiang Wang, Hongbo Bo, Jun Hong, Weiru Liu, Kedian Mu
HCPN-GCN is a graph-aware extension of Hierarchical Prototype Networks that replaces linear feature extractors with Graph Convolutional Networks and introduces cone-based prototypes with a diversity regularization objective. This design yields richer graph-aware representations, reduces prototype proliferation, and maintains near-zero forgetting. Experiments on six continual graph learning benchmarks show consistent accuracy improvements over the original HPN and other baselines while using roughly 30× fewer atomic prototypes.
By Sammuel R. Silva, Vander L. S. Freitas, Gladston Moreira, Eduardo J. S. Luz, Rodrigo Silva
arXiv:2512. 18295v2 Announce Type: replace-cross Abstract: Continual graph learning (CGL) aims to enable graph neural networks to incrementally learn from a stream of graph structured data without forgetting previously acquired knowledge.
By Xuling Zhang, Jindong Li, Yifei Zhang, Mingqi Yang, Menglin Yang
arXiv:2606. 00395v1 Announce Type: cross Abstract: Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale.
By Daize Dong, Junlin Chen, Haolong Jia, Jiawei Wu, Huanwei Di, Jiang Liu, Jialian Wu, Zhengzhong Liu, Zicheng Liu, Emad Barsoum, Dimitris N. Metaxas, Hongyi Wang
arXiv:2609.05862v1 Announce Type: new
Abstract: Learning on dynamic graphs is difficult when changes in the underlying network are only partially observed. Acquiring current graph information incurs...
By Zihe Zhou
MetaNet is a support‑set controller that predicts, for each layer of a Mixture‑of‑Experts model, an expert‑retention threshold and a bounded routing bias while keeping the backbone, experts, and router frozen. On DeepSeek‑MoE‑16B‑Chat, MetaNet offers a tunable trade‑off between accuracy and expert activation: a conservative setting activates 3.61 experts on average (40% fewer than a fixed k=6) with comparable MMLU accuracy, whereas an aggressive setting activates only 2.28 experts (62% fewer) with a modest accuracy drop. The MMLU‑trained controller also transfers to C‑Eval, activating 2.90 experts on average (52% fewer than fixed k=6) at 0.386 accuracy.
By Rongfeng Wang, Shichao Weng, Zhiqiang Wang, Xinyu Liu, Yang Yi, Peilong Zhou, Hongwei Tang
COMET is a task‑agnostic continual learning framework for vision‑language models that addresses modal‑consistency drift, representation‑space interference, and per‑task capacity shortfall. It uses a frozen teacher for feature reference, Tri‑Affinity Distillation to preserve image‑image, text‑text, and image‑text geometry, and Student‑Aware Cross‑Expert Distillation to align new experts with prior ones, while a contextual bandit and reconstruction router manage capacity and inference. Experiments on the X‑TAIL benchmark show that each component improves continual learning performance, demonstrating that separating feature reference, expert shaping, routing, and capacity control enables effective multimodal adaptation.
By Seungyoon Woo, Keonhee Park, Gunhee Kim
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
arXiv:2607. 12112v1 Announce Type: cross Abstract: Federated fine-tuning of Multimodal Large Language Models (MLLMs) across distributed networks enables privacy-sensitive adaptation to evolving data streams, yet a fundamental obstacle prevents robust deployment in dynamic environments: catastrophic forgetting, wherein sequential task updates erase previously acquired knowledge across visual, linguistic, and cross-modal representations.
By Jing Liu, Chenxuanyin Zou, Jiayang Ren, Gaoyun Fang, Chengfang Li, Yan Wang, Zhenchao Ma, Bo Hu