output
20152024
most citedFeature relevance quantification in explainable AI: A causal problem

156 citations

Showing 2021 · cs.LGShow all

24 papers · 2 filters

cs.LG20213 cited

Benchmarking Multimodal AutoML for Tabular Data with Text Fields

Xingjian Shi, Jonas Mueller, Nick Erickson +2

We consider the use of automated supervised learning systems for data tables that not only contain numeric/categorical columns, but one or more text fields as well. Here we assembl…

cs.LG20211 cited

Distributed Multi-Agent Deep Reinforcement Learning Framework for Whole-building HVAC Control

Vinay Hanumaiah, Sahika Genc

It is estimated that about 40%-50% of total electricity consumption in commercial buildings can be attributed to Heating, Ventilation, and Air Conditioning (HVAC) systems. Minimizi…

cs.LG202140 cited

Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud

Michaela Hardt, Xiaoguang Chen, Xiaoyi Cheng +18

Understanding the predictions made by machine learning (ML) models and their potential biases remains a challenging and labor-intensive task that depends on the application, the da…

cs.LG202133 cited

Rethinking Architecture Selection in Differentiable NAS

Ruochen Wang, Minhao Cheng, Xiangning Chen +2

Differentiable Neural Architecture Search is one of the most popular Neural Architecture Search (NAS) methods for its search efficiency and simplicity, accomplished by jointly opti…

cs.LG20211 cited

Fair Representation Learning using Interpolation Enabled Disentanglement

Akshita Jha, Bhanukiran Vinzamuri, Chandan K. Reddy

With the growing interest in the machine learning community to solve real-world problems, it has become crucial to uncover the hidden reasoning behind their decisions by focusing o…

cs.LG20211 cited

DeepTitle -- Leveraging BERT to generate Search Engine Optimized Headlines

Cristian Anastasiu, Hanna Behnke, Sarah Lück +3

Automated headline generation for online news articles is not a trivial task - machine generated titles need to be grammatically correct, informative, capture attention and generat…