Wenjun Wang

Change point detection in dynamic social graphs aims to identify significant transitions in evolving interaction patterns. The task is particularly challenging due to sparse and noisy interactions and frequent user turnover, while the existing methods largely overlook the semantic and emotional signals in user-generated content by focusing primarily on structural changes. To address these limitations, this paper proposes ECPD-SG, an emotion-aware contrastive prototype learning algorithm for unsupervised change point detection in dynamic social graphs. ECPD-SG constructs emotion-aware graph snapshots by integrating textual and affective features into node representations and recalibrating interaction weights through emotion-aware attention. It then summarizes temporal node representations into adaptive prototypes and models their evolution using optimal-transport-based alignment and contrastive learning. Change points are detected from prototype-level shift scores with an adaptive CUSUM decision rule. Experiments on real-world dynamic social graph datasets show that ECPD-SG achieves competitive or superior performance over representative baselines, while ablation and sensitivity analyses verify the effectiveness of its key components.

Roles of nodes refer to the structural patterns of relations that reflect node identities or functions in the graph or network. Learning role-based node representations has been a hot topic in the last decade, as they are helpful in fully understanding the internal mechanisms of the network and improving performance on downstream tasks. In real-world networks, the dependencies between the roles are extremely complex, where the local structures of nodes can vary considerably even if they share the same role. However, existing methods ignore the varying dependencies and fail to discover roles having the irregular structure. To fully understand the above problems, we first propose an index based on a graph kernel to measure role irregularity, and analyze its influence on downstream tasks. Then for practically overcoming the shortcomings, we propose a novel framework based on a graph neural network and a variational auto-encoder with a cross-attention mechanism (GVCAM). It leverages the graph convolutional network to preserve the varying dependencies between nodes and the variational auto-encoder to capture the structural traits of nodes. We introduce the crossattention mechanism that fuses the two parts to adaptively learn the irregular roles. Extensive experiments on one synthetic and six real-world datasets show that GVCAM achieves competitive performance across multiple tasks compared with ten state-of-the-art baselines.

Graph incremental learning aims to sequentially adapt models to evolving graphs while mitigating catastrophic forgetting. This problem becomes particularly challenging due to the simultaneous occurrence of covariate and label distribution shifts, introduced by newly emerging node classes, changes in node feature styles, and additional edges. To address these challenges, we propose DINGLE, a novel framework for both class and domain (class-domain) incremental learning on graphs. DINGLE consists of two key modules: a representation decoupler, which disentangles node representations into domain-invariant semantic factors for classification and domain-specific variation factors, and a teacher-student knowledge distillation module, which facilitates knowledge transfer across tasks while mitigating catastrophic forgetting through memory replay. By leveraging a Representative Node Feature (RNF) bank and an Encoder Parameters (EP) bank, DINGLE ensures effective knowledge retention and adaptation. Extensive experiments on 5 real-world datasets demonstrate that DINGLE outperforms 11 state-of-the-art baselines in class-domain incremental learning, improving classification accuracy while effectively preventing forgetting across tasks.