MTL November 3, 2020 Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations Let's go beyond the negative transfer and seesaw phenomenon! #Multi-Task Learning #Deep Learning #Machine Learning #Recommender System
NLP October 24, 2020 BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Get the ultimate pre-trained features applicable to any language model #NLP
Statistical Learning October 19, 2020 Sampling methods for statistical inference Several important sampling methods used in Bayesian statistics #Statistics #Bayesian Statistics #Statistical Learning #Machine Learning
Statistical Learning October 17, 2020 Active Learning for Community Detection in Stochastic Block Models Is community recovery possible even when D(a, b) < 1 in a symmetric SBM environment? #Stochastic Block Model #Statistical Learning #Active Learning
Statistical Learning September 16, 2020 Stochastic Blockmodels meet Graph Neural Networks Latent Feature Modeling via Indian Buffet Process with Graph Neural Networks. #GNN #Statistical Learning #XAI
Network Analysis September 4, 2020 Basic models and questions in statistical network analysis (Lecture 1) How can we test whether an algorithm performs well? What are the fundamental limits to any community detection algorithm? #Machine Learning #Statistiacl Learninig
GNN August 28, 2020 Block Model Guided Unsupervised Feature Selection How to effectively select features by utilizing SBM. #Datamining #GNN #Machine Learning
XAI July 31, 2020 Interpreting Deep Neural Networks Through Variable Importance Given a trained model, which features are the most important? #XAI #Statistical Learning
Deep Learning Theory July 19, 2020 Yarin Gal Thesis (Uncertainty in Deep Learning) Chapter 3 Find out relation between Dropout and Bayesian NN. #Deep Learning #Machine Learning #Statistical Learning
GNN July 2, 2020 Fourier and Wavelet transform in GCN Understanding Fourier and Wavelet transforms in GCN #GNN #Mathematics #Signal Processing