NeurIPS 2022 in New Orleans
Zhang Ce attended the 36th Conference on Neural Information Processing Systems (NeurIPS-22), which took place 28 November through 9 December, 2022. After two-year virtual...
Recent Posts
KDD 2022 in Washington, D.C.
In August 2022, Hady, Zhang Ce, and Thuat travelled to Washington D.C. to attend the 28th ACM SIGKDD Conference on Knowledge Discovery and Data...
Preferably Nonsentimental Defense of Sentiments and Preferences
On 10 February 2022, Tuan Truong successfully defended his dissertation, entitled “Modeling Sentiments and Preferences from Multimodal Data”. In a sign of the times,...
Multi-Modal Recommender Systems: Hands-On Exploration
Tuan, Aghiles, and Hady will be delivering a tutorial at the RecSys-21 conference that will take place in September 2021. The slides and the...
Fast and Accurate Personalized Recommendation with Indexing
In a previous blog post, we introduce the problem of top-K recommendation retrieval using Matrix Factorization (MF). We also highlight the importance of indexing structures as a...
A Quest for Fast Personalized Recommendation
Personalized recommender systems attempt to generate a limited number of item options (e.g., products on Amazon, movies on Netflix, or videos on Youtube, etc.)...
Zooming in on TechFest 2020
Join us for TechFest 2020 by Preferred.AI! Our theme this year is Zooming In. Inside an innovative app is a cool AI algorithm. On...
Visual Sentiment Analysis: A Need for Context
Previously, we gave our readers a glance at visual sentiment analysis in an earlier blog post. The goal of the task was seeking the...
Neural Topic Modeling for Document Networks with Adjacent-Encoder
Text documents are usually linked to one another. For example, academic papers cite other papers, web pages link to other pages, etc. Most of...
Why maximum likelihood-based training may lead to the generation of unrealistic samples
Generative models specify procedures allowing us to produce data samples, e.g., images, texts, user preferences, etc. These models are central to unsupervised learning, and...
