首页|Researchers from University of Bari Publish Research in Machine Learning (Machin e Learning and Knowledge Graphs: Existing Gaps and Future Research Challenges)
Researchers from University of Bari Publish Research in Machine Learning (Machin e Learning and Knowledge Graphs: Existing Gaps and Future Research Challenges)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on artificial in telligence have been published. According to news originating from the Universit y of Bari by NewsRx correspondents, research stated, “The graph model is nowaday s largely adopted to model a wide range of knowledge and data, spanning from soc ial networks to knowledge graphs (KGs), representing a successful paradigm of ho w symbolic and transparent AI can scale on the World Wide Web.” The news journalists obtained a quote from the research from University of Bari: “However, due to their unprecedented volume, they are generally tackled by Mach ine Learning (ML) and mostly numeric based methods such as graph embedding model s (KGE) and deep neural networks (DNNs). The latter methods have been proved lat ely very efficient, leading the current AI spring. In this vision paper, we intr oduce some of the main existing methods for combining KGs and ML, divided into t wo categories: those using ML to improve KGs, and those using KGs to improve res ults on ML tasks. From this introduction, we highlight research gaps and perspec tives that we deem promising and currently under-explored for the involved resea rch communities, spanning from KG support for LLM prompting, integration of KG s emantics in ML models to symbol-based methods, interpretability of ML models, an d the need for improved benchmark datasets.”
University of BariCyborgsEmerging Te chnologiesMachine Learning
NETL
NSTL
