Contrast then Memorize: Semantic Neighbor Retrieval-Enhanced Inductive Multimodal Knowledge Graph Completion
Offered By: Association for Computing Machinery (ACM) via YouTube
Course Description
Overview
Explore a 15-minute conference talk presented at SIGIR 2024 focusing on innovative approaches to inductive multimodal knowledge graph completion. Delve into the "Contrast then Memorize" method, which enhances semantic neighbor retrieval for more effective graph completion. Learn how authors Yu Zhao, Ying Zhang, Baohang Zhou, Xinying Qian, Kehui Song, and Xiangrui Cai tackle the challenges of reasoning and knowledge graph expansion. Gain insights into cutting-edge techniques that combine contrastive learning and memorization strategies to improve the accuracy and efficiency of multimodal knowledge graph completion in inductive settings.
Syllabus
SIGIR 2024 M1.2 [fp] Contrast then Memorize: Semantic Neighbor Retrieval-Enhanced Inductive Multimod
Taught by
Association for Computing Machinery (ACM)
Related Courses
Stanford Seminar - Audio Research: Transformers for Applications in Audio, Speech and MusicStanford University via YouTube How to Represent Part-Whole Hierarchies in a Neural Network - Geoff Hinton's Paper Explained
Yannic Kilcher via YouTube OpenAI CLIP - Connecting Text and Images - Paper Explained
Aleksa Gordić - The AI Epiphany via YouTube Learning Compact Representation with Less Labeled Data from Sensors
tinyML via YouTube Human Activity Recognition - Learning with Less Labels and Privacy Preservation
University of Central Florida via YouTube