IEEE

GNN-EADD: Graph Neural Network-Based E-Commerce Anomaly Detection via Dual-Stage Learning

Abstract: E-commerce platforms face significant challenges in detecting anomalous products, including counterfeit goods and fraudulent listings, which can undermine user trust and platform integrity.
IEEE

TGformer: A Graph Transformer Framework for Knowledge Graph Embedding

Abstract: Knowledge graph embedding is efficient method for reasoning over known facts and inferring missing links. Existing methods are mainly triplet-based or graph-based. Triplet-based approaches ...
Bleeping Computer

Google Gemini flaw hijacks email summaries for phishing

Google Gemini for Workspace can be exploited to generate email summaries that appear legitimate but include malicious instructions or warnings that direct users to phishing sites without using ...
Scientific Research Publishing

Gordon, D., Petousis, P., Zheng, H., Zamanzadeh, D. and Bui, A.A.T. (2021) TSI-GNN: Extending Graph Neural Networks to Handle Missing Data in Temporal Settings. Frontiers in ...

ABSTRACT: Missing data remains a persistent and pervasive challenge across a wide range of domains, significantly impacting data analysis pipelines, predictive modeling outcomes, and the reliability ...
GitHub

RFC for TPU Embedding (name TBD)

We are working on a new library, Keras RS (Keras Recommender Systems). Part of this new library will be the Keras 3 multi-backend successor of TFRS' TPUEmbedding. This layer groups multiple embeddings ...
GitHub

mSWE-GNN (Repository for paper "Multi-scale hydraulic graph neural networks for flood modelling")

models: Deep learning models developed for surrogating the hydraulic one: contains a base class with common inputs and functions and one for the SWE-GNN and mSWE-GNN models. results: Contains results ...