Don't miss any moment of global AI innovation
Daily three-minute AI industry trends
AI industry milestones
AI monetization case sharing
AI image creation monetization cases
AI video creation monetization cases
AI audio creation monetization cases
AI content writing monetization cases
Free sharing of the latest AI tutorials
Shows total visits ranking of AI websites
Track fastest growing AI websites by traffic
Focus on AI websites with significant traffic drops
Shows weekly visits ranking of AI websites
AI websites most popular with US users
AI websites most popular with Chinese users
AI websites most popular with Indian users
AI websites most popular with Brazilian users
Total visits ranking of AI image generation websites
Total visits ranking of AI personal assistant websites
Total visits ranking of AI character generation websites
Total visits ranking of AI video generation websites
GitHub popular AI projects by total stars
GitHub popular AI projects by growth rate
GitHub popular AI developer ranking
GitHub popular AI organization ranking
GitHub popular deepseek open source projects
GitHub popular TTS open source projects
GitHub popular LLM open source projects
GitHub popular ChatGPT open source projects
Overview of GitHub popular AI open source projects
Graph Neural Networks (GNN) Experimentation Playground
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ???
PyTorch implementation of Pointnet2/Pointnet++
An Industrial Graph Neural Network Framework
An index of recommendation algorithms that are based on Graph Neural Networks. (TORS)
Flexible components pairing ? Transformers with :zap: Pytorch Lightning
Code and resources on scalable and efficient Graph Neural Networks (TNNLS 2023)
A PyTorch Graph Neural Network Library
PyTorch implementation of MTAD-GAT (Multivariate Time-Series Anomaly Detection via Graph Attention Networks) by Zhao et. al (2020, https://arxiv.org/abs/2009.02040).
Federated learning on graph, especially on graph neural networks (GNNs), knowledge graph, and private GNN.
1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and GraphSAGE based on message passing.