Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of GraphSearch.
This lecture introduces contrastive losses for representation learning, focusing on Word2Vec and Skip-gram models. It covers the training objectives, context windows, negative sampling, and Noise Contrastive Estimation. The lecture also explores InfoNCE/CPC and its applications in image and graph data, as well as related topics like Deep Metric Learning and Energy-based models.