Search Results for author: Jianxi Gao

Found 10 papers, 1 papers with code

Spatio-Temporal Graphical Counterfactuals: An Overview

no code implementations2 Jul 2024 Mingyu Kang, Duxin Chen, Ziyuan Pu, Jianxi Gao, Wenwu Yu

Counterfactual thinking is a critical yet challenging topic for artificial intelligence to learn knowledge from data and ultimately improve their performances for new scenarios.

counterfactual

On the Robustness of Language Models for Tabular Question Answering

no code implementations18 Jun 2024 Kushal Raj Bhandari, Sixue Xing, Soham Dan, Jianxi Gao

Large Language Models (LLMs), originally shown to ace various text comprehension tasks have also remarkably been shown to tackle table comprehension tasks without specific training.

In-Context Learning Question Answering +1

Graph is all you need? Lightweight data-agnostic neural architecture search without training

no code implementations2 May 2024 Zhenhan Huang, Tejaswini Pedapati, Pin-Yu Chen, Chunhen Jiang, Jianxi Gao

Our method, dubbed nasgraph, remarkably reduces the computational costs by converting neural architectures to graphs and using the average degree, a graph measure, as the proxy in lieu of the evaluation metric.

Neural Architecture Search

Bullwhip Effect of Supply Networks: Joint Impact of Network Structure and Market Demand

no code implementations8 Aug 2022 Jin-Zhu Yü, Chencheng Cai, Jianxi Gao

The progressive amplification of fluctuations in demand as the demand travels upstream the supply chains is known as the bullwhip effect.

Position

Reconstructing Sparse Multiplex Networks with Application to Covert Networks

1 code implementation29 Jul 2022 Jin-Zhu Yu, Mincheng Wu, Gisela Bichler, Felipe Aros-Vera, Jianxi Gao

For law enforcement agencies, the inferred complete network structure can be used to develop more effective strategies for covert network interdiction.

Decision Making

Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics

no code implementations11 Jan 2022 Chunheng Jiang, Tejaswini Pedapati, Pin-Yu Chen, Yizhou Sun, Jianxi Gao

To this end, we construct a network mapping $\phi$, converting a neural network $G_A$ to a directed line graph $G_B$ that is defined on those edges in $G_A$.

Model Selection

Universality of noise-induced resilience restoration in spatially-extended ecological systems

no code implementations24 Nov 2020 Cheng Ma, Gyorgy Korniss, Boleslaw K. Szymanski, Jianxi Gao

Resilience restoration focuses on the ability of spatially-extended systems and the required time to recover to their desired states under stochastic environmental conditions.

Network resilience

no code implementations26 Jul 2020 Xueming Liu, Daqing Li, Manqing Ma, Boleslaw K. Szymanski, H. Eugene Stanley, Jianxi Gao

Many systems on our planet are known to shift abruptly and irreversibly from one state to another when they are forced across a "tipping point," such as mass extinctions in ecological networks, cascading failures in infrastructure systems, and social convention changes in human and animal networks.

Modeling competitive evolution of multiple languages

no code implementations16 Jul 2019 Zejie Zhou, Boleslaw K. Szymanski, Jianxi Gao

Our analysis furthers our understanding of multiple language evolution and the role of tipping points in behavioral transitions.

Diversity

Cannot find the paper you are looking for? You can Submit a new open access paper.