AI models retrace evolution of genetic control elements in the brain

Artificial intelligence allows tracing the evolution of genetic control elements in the developing mammalian cerebellum. An international research team led by biologists from Heidelberg University as ...
IEEE

Graph Split Federated Learning for Distributed Large-Scale AIoT in Smart Cities

Abstract: The rise of smart cities has leveraged the power of Internet of Things devices to transform urban services. A key element of this transformation is the widespread deployment of IoT devices ...
GitHub

DShield: Defending against Backdoor Attacks on Graph Neural Networks via Discrepancy Learning

Graph Neural Networks (GNNs) are vulnerable to backdoor attacks, where triggers inserted into original graphs cause adversary-determined predictions. Backdoor attacks on GNNs, typically focusing on ...
University of Gothenburg

The Phenomenography and Variation Theory Global Network

The Phenomenography and Variation Theory Global Network is an independent, international scholarly community bringing together researchers working within, alongside, and informed by phenomenography ...
lse

Learning from a single network: How new mathematics reveals the hidden geometry of graphs

Giulia Livieri sets out remarkable new research with results that clarify how learning works on complex graphs and how quickly any method (including Graph Convolutional Networks) can learn from them, ...
IEEE

LYRICEL: Knowledge Graphs Combined With Large Language Models and Machine Learning for Cross-Cultural Analysis of Lyrics—The Case of Greek Songs

Abstract: This paper presents LYRICEL, a framework integrating Knowledge Graph (KG) representation learning, Large Language Models (LLMs), and machine learning for reliable, explainable, and ...