Tagged
Contrastive Learning
Recommendation Systems (11): Contrastive Learning and Self-Supervised Learning
A practitioner's guide to contrastive learning for recommendations: InfoNCE and the role of temperature, SimCLR vs MoCo negatives, SGL graph augmentations, CL4SRec sequence augmentations, XSimGCL's noise-only trick, with …
Transfer Learning (8): Multimodal Transfer
Derive contrastive learning (InfoNCE), CLIP's vision-language pretraining, BLIP's Q-Former bridge to LLMs, cross-modal alignment, and multimodal fusion strategies. Includes a from-scratch CLIP implementation in PyTorch.
HCGR: Hyperbolic Contrastive Graph Representation Learning for Session-based Recommendation
HCGR embeds session graphs in the Lorentz model of hyperbolic space and trains them with InfoNCE-style contrastive learning. This review unpacks why hierarchical session intent fits hyperbolic geometry, how Lorentz …