332 citations
- IBM (United States)US24 papers
- Massachusetts Institute of TechnologyUS5 papers
- IBM Research - ZurichCH3 papers
- University of California, Los AngelesUS3 papers
- IBM Research - Thomas J. Watson Research CenterUS2 papers
- University of California, BerkeleyUS2 papers
- Austrian Academy of SciencesAT1 paper
- Berkeley CollegeUS1 paper
- Binghamton UniversityUS1 paper
- Boston Scientific (United States)US1 paper
- Brown UniversityUS1 paper
- California Institute of TechnologyUS1 paper
7 papers · 1 filter
Local Off-Grid Weather Forecasting with Multi-Modal Earth Observation Data
Qidong Yang, Jonathan Giezendanner, Daniel Salles Civitarese +8
Urgent applications like wildfire management and renewable energy generation require precise, localized weather forecasts near the Earth's surface. However, forecasts produced by m…
When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark
Junhong Lin, Xiaojie Guo, Shuaicheng Zhang +2
Graph mining has become crucial in fields such as social science, finance, and cybersecurity. Many large-scale real-world networks exhibit both heterogeneity, where multiple node a…
A Transformer-based Framework for Multivariate Time Series Representation Learning
George Zerveas, Srideepika Jayaraman, Dhaval Patel +2
In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially…
Efficient Neural Network Robustness Certification with General Activation Functions
Huan Zhang, Tsui-Wei Weng, Pin-Yu Chen +2
Finding minimum distortion of adversarial examples and thus certifying robustness in neural network classifiers for given data points is known to be a challenging problem. Neverthe…
On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm
Tsui-Wei Weng, Huan Zhang, Pin-Yu Chen +3
CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extreme Value Theory (EVT) based robustness score for large-scale deep neural networks (DNNs). In this paper, we…
An Upper Bound for Random Measurement Error in Causal Discovery
Tineke Blom, Anna Klimovskaia, Sara Magliacane +1
Causal discovery algorithms infer causal relations from data based on several assumptions, including notably the absence of measurement error. However, this assumption is most like…