Consequently,thenoisy-to-clean transformation learned from the training data cannot be suitably applied to handle the testing noise, resulting in limited enhancement performance.

Graph class incremental learning (GCIL) requires the model to classify emerging nodes of new classes while remembering old classes. Existing methods are designed to preserve effective information of old models or graph data to alleviate forgetting, but there is no clear theoretical understanding of what matters in information preservation.

Meanwhile,adding self-loops makes the greatest common divisor of the lengths of graph'scycles is 1. Clearly,πappr is upper bounded by πappr 1. To support the reproducibility of the results in this paper, we detail datasets, the baseline settings pseudocode and model implementation in experiments. In this paper, we usemean as its aggregator since it performs best [7].

Inthis paper,we theoretically extend spectral-based graph convolution todigraphs and deriveasimplified form usingpersonalizedPageRank. Specifically,we present theDigraph Inception Convolutional Networks(DiGCN) whichutilizes digraph convolution andkth-order proximity to achievelarger receptivefields and learn multi-scale features in digraphs.

Several approaches to predictive uncertainty quantification have been introduced in recent years, considering uncertainty inaBayesian sense [2,7,18]aswell asfrom afrequentist'spoint ofview [15,5,34].