Dehua Cheng
YOU?
Author Swipe
View article: Towards Automated Model Design on Recommender Systems
Towards Automated Model Design on Recommender Systems Open
The increasing popularity of deep learning models has created new opportunities for developing artificial intelligence–based recommender systems. Designing recommender systems using deep neural networks (DNNs) requires careful architecture…
View article: Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale
Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale Open
Neural Architecture Search (NAS) has demonstrated its efficacy in computer vision and potential for ranking systems. However, prior work focused on academic problems, which are evaluated at small scale under well-controlled fixed baselines…
View article: Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale
Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale Open
Neural Architecture Search (NAS) has demonstrated its efficacy in computer vision and potential for ranking systems. However, prior work focused on academic problems, which are evaluated at small scale under well-controlled fixed baselines…
View article: Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection
Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection Open
Recommendation is a prevalent application of machine learning that affects many users; therefore, it is important for recommender models to be accurate and interpretable. In this work, we propose a method to both interpret and augment the …
View article: Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection
Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection Open
Recommendation is a prevalent application of machine learning that affects many users; therefore, it is important for recommender models to be accurate and interpretable. In this work, we propose a method to both interpret and augment the …
View article: Detecting Statistical Interactions from Neural Network Weights
Detecting Statistical Interactions from Neural Network Weights Open
Interpreting neural networks is a crucial and challenging task in machine learning. In this paper, we develop a novel framework for detecting statistical interactions captured by a feedforward multilayer neural network by directly interpre…
View article: Spectral Sparsification of Random-Walk Matrix Polynomials
Spectral Sparsification of Random-Walk Matrix Polynomials Open
We consider a fundamental algorithmic question in spectral graph theory: Compute a spectral sparsifier of random-walk matrix-polynomial $$L_α(G)=D-\sum_{r=1}^dα_rD(D^{-1}A)^r$$ where $A$ is the adjacency matrix of a weighted, undirected gr…