6 papers · 1 filter
Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts
Yue Hou, Ruomei Liu, Yingke Su +2
Deep graph learning models deployed in real-world systems often need to cope with non-stationary environments, where the underlying graph distribution drifts continually over time.…
Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries
Yue Hou, Ruomei Liu, Yingke Su +2
A key challenge in graph out-of-distribution (OOD) detection lies in the absence of ground-truth OOD samples during training. Existing methods are typically optimized to capture fe…
Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
Yue Hou, He Zhu, Ruomei Liu +3
Distributional discrepancy between training and test data can lead models to make inaccurate predictions when encountering out-of-distribution (OOD) samples in real-world applicati…
Structural Entropy Guided Unsupervised Graph Out-Of-Distribution Detection
Yue Hou, He Zhu, Ruomei Liu +4
With the emerging of huge amount of unlabeled data, unsupervised out-of-distribution (OOD) detection is vital for ensuring the reliability of graph neural networks (GNNs) by identi…
Molecular Graph Contrastive Learning with Line Graph
Xueyuan Chen, Shangzhe Li, Ruomei Liu +4
Trapped by the label scarcity in molecular property prediction and drug design, graph contrastive learning (GCL) came forward. Leading contrastive learning works show two kinds of…
NC-NCD: Novel Class Discovery for Node Classification
Yue Hou, Xueyuan Chen, He Zhu +5
Novel Class Discovery (NCD) involves identifying new categories within unlabeled data by utilizing knowledge acquired from previously established categories. However, existing NCD…