Abstract: Systems, storage media and methods for generating task significance information is described. The system may receive task information for a plurality of tasks; generate a task graph based on the received task information, wherein the task graph includes a plurality of nodes and at least one node of the plurality of nodes is generated for at least one task of the plurality of tasks; assign an edge type to an edge existing between the at least one node of the plurality of nodes and another node in the task graph; generate, based on at least a portion of the task graph including the edge type, task significance information for at least one task of the plurality tasks; and update at least one graphical representation of a task displayed at a user interface based on the task significance information.

Abstract: A system employs Graph Prototypical Networks (GPN) for few-shot node classification on attributed networks, and a meta-learning framework trains the system by constructing a pool of semi-supervised node classification tasks to mimic the real test environment. The system is able to perform meta-learning on an attributed network and derive a highly generalizable model for handling the target classification task. The meta-learning framework addresses extraction of meta-knowledge from an attributed network for few-shot node classification, and identification of the informativeness of each labeled instance for building a robust and effective model.

Abstract: Various embodiments for few-shot network anomaly detection via cross-network meta-learning are disclosed herein. An anomaly detection system incorporating a new family of graph neural networks—Graph Deviation Networks (GDN) can leverage a small number of labeled anomalies for enforcing statistically significant deviations between abnormal and normal nodes on a network. Further, the GDN is equipped with a new cross-network meta-learning algorithm (Meta-GDN) to realize few-shot network anomaly detection by transferring meta-knowledge from multiple auxiliary networks. Extensive evaluations demonstrate the efficacy of the anomaly detection system and the Meta-GDN on few-shot or even one-shot network anomaly detection.

Abstract: Various embodiments of systems and methods for inductive anomaly detection on attributed networks using a graph neural layer to learn anomaly-aware node representations and further employ generative adversarial learning to detect anomalies among new data are disclosed herein.