Continual learning on graph data, which aims to accommodate new tasks over newly emerged graph data while maintaining the model performance over existing tasks, is attracting increasing attention from the community. Unlike continual learning on Euclidean data ($\textit{e.g.}$, images, texts, etc.) that has established benchmarks and unified experimental settings, benchmark tasks are rare for Continual Graph Learning (CGL). Moreover, due to the variety of graph data and its complex topological structures, existing works adopt different protocols to configure datasets and experimental settings. This creates a great obstacle to compare different techniques and thus hinders the development of CGL. To this end, we systematically study the task configurations in different application scenarios and develop a comprehensive Continual Graph Learning Benchmark (CGLB) curated from different public datasets. Specifically, CGLB contains both node-level and graph-level continual graph learning tasks under task-incremental (currently widely adopted) and class-incremental (more practical, challenging, yet underexplored) settings, as well as a toolkit for training, evaluating, and visualizing different CGL methods.

Unlike continual learning on Euclidean data ( e.g., images, texts, etc.) that has established benchmarks

Heterogeneous graph neural networks have seen rapid progress in web applications such as social networks, knowledge graphs, and recommendation systems, driven by the inherent heterogeneity of web data. However, existing methods typically assume static graphs, while real-world graphs are continuously evolving. This dynamic nature requires models to adapt to new data while preserving existing knowledge. To this end, this work introduces HERO (HEterogeneous continual gRaph learning via meta-knOwledge distillation), a unified framework for continual learning on heterogeneous graphs. HERO employs meta-adaptation, a gradient-based meta-learning strategy that provides directional guidance for rapid adaptation to new tasks with limited samples. To enable efficient and effective knowledge reuse, we propose DiSCo (Diversity Sampling with semantic Consistency), a heterogeneity-aware sampling method that maximizes target node diversity and expands subgraphs along metapaths, retaining critical semantic and structural information with minimal overhead. Furthermore, HERO incorporates heterogeneity-aware knowledge distillation, which aligns knowledge at both the node and semantic levels to balance adaptation and retention across tasks. Extensive experiments on four web-related heterogeneous graph benchmarks demonstrate that HERO substantially mitigates catastrophic forgetting while achieving efficient and consistent knowledge reuse in dynamic web environments.

Catastrophic forgetting is one of the main obstacles for Online Continual Graph Learning (OCGL), where nodes arrive one by one, distribution drifts may occur at any time and offline training on task-specific subgraphs is not feasible. In this work, we explore a surprisingly simple yet highly effective approach for OCGL: we use a fixed, randomly initialized encoder to generate robust and expressive node embeddings by aggregating neighborhood information, training online only a lightweight classifier. By freezing the encoder, we eliminate drifts of the representation parameters, a key source of forgetting, obtaining embeddings that are both expressive and stable. When evaluated across several OCGL benchmarks, despite its simplicity and lack of memory buffer, this approach yields consistent gains over state-of-the-art methods, with surprising improvements of up to 30% and performance often approaching that of the joint offline-training upper bound. These results suggest that in OCGL, catastrophic forgetting can be minimized without complex replay or regularization by embracing architectural simplicity and stability.

Continual Graph Learning(CGL)focuses on acquiring new knowledge while retaining previously learned information, essential for real-world graph applications. Current methods grapple with two main issues:1) The Stability-Plasticity Dilemma: Replay-based methods often create an imbalance between the Dilemma, while incurring significant storage costs.2) The Resource-Heavy Pre-training: Leading replay-free methods critically depend on extensively pre-trained backbones, this reliance imposes a substantial resource burden.In this paper, we argue that the key to overcoming these challenges lies not in replaying data or fine-tuning the entire network, but in dynamically modulating the internal computational flow of a frozen backbone. We posit that lightweight, task-specific modules can effectively steer a GNN's reasoning process. Motivated by this insight, we propose Task-Aware Adaptive Modulation(TAAM), a replay-free, resource-efficient approach that charts a new path for navigating the stability-plasticity dilemma. TAAM's core is its Neural Synapse Modulators(NSM), which are trained and then frozen for each task to store expert knowledge. A pivotal prototype-guided strategy governs these modulators: 1) For training, it initializes a new NSM by deep-copying from a similar past modulator to boost knowledge transfer. 2) For inference, it selects the most relevant frozen NSM for each task. These NSMs insert into a frozen GNN backbone to perform fine-grained, node-attentive modulation of its internal flow-different from the static perturbations of prior methods. Extensive experiments show that TAAM comprehensively outperforms state-of-the-art methods across six GCIL benchmark datasets. The code will be released upon acceptance of the paper.

Unlike continual learning on Euclidean data ( e.g., images, texts, etc.) that has established benchmarks

Graph Neural Networks (GNNs) experience "catastrophic forgetting" in continual learning setups, where they tend to lose previously acquired knowledge and perform poorly on old tasks. Rehearsal-based methods, which consolidate old knowledge with a replay memory buffer, are a de facto solution due to their straightforward workflow. However, these methods often fail to adequately capture topological information, leading to incorrect input-label mappings in replay samples. To address this, we propose TACO, a topology-aware graph coarsening and continual learning framework that stores information from previous tasks as a reduced graph. Throughout each learning period, this reduced graph expands by integrating with a new graph and aligning shared nodes, followed by a "zoom-out" reduction process to maintain a stable size.

Financial institutions are required by regulation to report suspicious financial transactions related to money laundering. Therefore, they need to constantly monitor vast amounts of incoming and outgoing transactions. A particular challenge in detecting money laundering is that money launderers continuously adapt their tactics to evade detection. Hence, detection methods need constant fine-tuning. Traditional machine learning models suffer from catastrophic forgetting when fine-tuning the model on new data, thereby limiting their effectiveness in dynamic environments. Continual learning methods may address this issue and enhance current anti-money laundering (AML) practices, by allowing models to incorporate new information while retaining prior knowledge. Research on continual graph learning for AML, however, is still scarce. In this review, we critically evaluate state-of-the-art continual graph learning approaches for AML applications. We categorise methods into replay-based, regularization-based, and architecture-based strategies within the graph neural network (GNN) framework, and we provide in-depth experimental evaluations on both synthetic and real-world AML data sets that showcase the effect of the different hyperparameters. Our analysis demonstrates that continual learning improves model adaptability and robustness in the face of extreme class imbalances and evolving fraud patterns. Finally, we outline key challenges and propose directions for future research.

Continual learning on graph data, which aims to accommodate new tasks over newly emerged graph data while maintaining the model performance over existing tasks, is attracting increasing attention from the community. Unlike continual learning on Euclidean data ( \textit{e.g.}, images, texts, etc.) that has established benchmarks and unified experimental settings, benchmark tasks are rare for Continual Graph Learning (CGL). Moreover, due to the variety of graph data and its complex topological structures, existing works adopt different protocols to configure datasets and experimental settings. This creates a great obstacle to compare different techniques and thus hinders the development of CGL. To this end, we systematically study the task configurations in different application scenarios and develop a comprehensive Continual Graph Learning Benchmark (CGLB) curated from different public datasets. Specifically, CGLB contains both node-level and graph-level continual graph learning tasks under task-incremental (currently widely adopted) and class-incremental (more practical, challenging, yet underexplored) settings, as well as a toolkit for training, evaluating, and visualizing different CGL methods.

Continual learning has emerged as a crucial paradigm for learning from sequential data while preserving previous knowledge. In the realm of continual graph learning, where graphs continuously evolve based on streaming graph data, continual graph learning presents unique challenges that require adaptive and efficient graph learning methods in addition to the problem of catastrophic forgetting. The first challenge arises from the interdependencies between different graph data, where previous graphs can influence new data distributions. The second challenge lies in the efficiency concern when dealing with large graphs. To addresses these two problems, we produce an Efficient Continual Graph Learner (E-CGL) in this paper. We tackle the interdependencies issue by demonstrating the effectiveness of replay strategies and introducing a combined sampling strategy that considers both node importance and diversity. To overcome the limitation of efficiency, E-CGL leverages a simple yet effective MLP model that shares weights with a GCN during training, achieving acceleration by circumventing the computationally expensive message passing process. Our method comprehensively surpasses nine baselines on four graph continual learning datasets under two settings, meanwhile E-CGL largely reduces the catastrophic forgetting problem down to an average of -1.1%. Additionally, E-CGL achieves an average of 15.83x training time acceleration and 4.89x inference time acceleration across the four datasets. These results indicate that E-CGL not only effectively manages the correlation between different graph data during continual training but also enhances the efficiency of continual learning on large graphs. The code is publicly available at https://github.com/aubreygjh/E-CGL.