Considering local and bounded-size neighborhoods of knowledge bases renders logical inference and learning tractable, mitigates the problem of overfitting, and facilitates weight sharing.

The "black-box" nature of representations, combined with the known susceptibility of networks to learn spurious correlations [

However, these models suffer from quadratic computational cost in the input sequence lengthn to compute pairwise attention in each layer.

Recently,researchers extended 1-hop message passing to K-hop message passing by aggregating information fromK-hop neighbors of nodes simultaneously. However, there is no work on analyzing the expressive powerofK-hopmessagepassing.

Graph Anomaly Detection (GAD) aims to identify uncommon, deviated, or suspicious objects within graph-structured data. Existing methods generally focus on a single graph object type (node, edge, graph, etc.) and often overlook the inherent connections among different object types of graph anomalies. For instance, a money laundering transaction might involve an abnormal account and the broader community it interacts with. To address this, we present UniGAD, the first unified framework for detecting anomalies at node, edge, and graph levels jointly. Specifically, we develop the Maximum Rayleigh Quotient Subgraph Sampler (MRQSampler) that unifies multi-level formats by transferring objects at each level into graph-level tasks on subgraphs.