NeurIPS 2023 Research Highlights - Circuits, Collaborative Filtering, Clustering, and Privacy

Explore cutting-edge machine learning research presented at NeurIPS 2023 in this conference talk video. Dive into four innovative papers covering topics like using graph neural networks to optimize circuit design, improving collaborative filtering with adversarial contrastive loss, advancing semi-supervised learning through cluster-aware approaches, and evaluating privacy metrics for reconstructed images. Gain insights into the latest developments in graph neural networks, recommendation systems, semi-supervised learning, and privacy-preserving machine learning techniques. Follow along as each paper is summarized and discussed, providing a comprehensive overview of these impactful contributions to the field of artificial intelligence and machine learning.

Syllabus

- Intro
- Graph of Circuits with GNN for Exploring the Optimal Design Space
- Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss
- Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering
- Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?