Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks

Kavli Affiliate: Xiang Zhang | First 5 Authors: Tianxiang Zhao, Xiang Zhang, Suhang Wang, , | Summary: In recent years, graph neural networks (GNNs) have achieved state-of-the-art performance for node classification. However, most existing GNNs would suffer from the graph imbalance problem. In many real-world scenarios, node classes are imbalanced, with some majority classes making […]


Continue.. Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks

Dynamics of fractionalized mean-field theories: consequences for Kitaev materials

Kavli Affiliate: Joel E. Moore | First 5 Authors: Tessa Cookmeyer, Joel E. Moore, , , | Summary: There have been substantial recent efforts, both experimentally and theoretically, to find a material realization of the Kitaev spin-liquid–the ground state of the exactly solvable Kitaev model on the honeycomb lattice. Candidate materials are now plentiful, but […]


Continue.. Dynamics of fractionalized mean-field theories: consequences for Kitaev materials

Nonadiabatic transition paths from quantum jump trajectories

Kavli Affiliate: David T. Limmer | First 5 Authors: Michelle C. Anderson, Addison J. Schile, David T. Limmer, , | Summary: We present a means of studying rare reactive pathways in open quantum systems using Transition Path Theory and ensembles of quantum jump trajectories. This approach allows for elucidation of reactive paths for dissipative, nonadiabatic […]


Continue.. Nonadiabatic transition paths from quantum jump trajectories

Minimal Joint Entropy and Order-Preserving Couplings

Kavli Affiliate: Feng Wang | First 5 Authors: Ya-Jing Ma, Feng Wang, Xian-Yuan Wu, Kai-Yuan Cai, | Summary: This paper focuses on the extreme-value problem for Shannon entropy of the joint distribution with given marginals. It is proved that the minimum-entropy coupling must be of order-preserving, while the maximum-entropy coupling coincides with the independent one. […]


Continue.. Minimal Joint Entropy and Order-Preserving Couplings

Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition

Kavli Affiliate: Feng Wang | First 5 Authors: Guangke Chen, Zhe Zhao, Fu Song, Sen Chen, Lingling Fan | Summary: Speaker recognition systems (SRSs) have recently been shown to be vulnerable to adversarial attacks, raising significant security concerns. In this work, we systematically investigate transformation and adversarial training based defenses for securing SRSs. According to […]


Continue.. Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition

Effects of Laser-Annealing on Fixed-Frequency Superconducting Qubits

Kavli Affiliate: Irfan Siddiqi | First 5 Authors: Hyunseong Kim, Christian Jünger, Alexis Morvan, Edward S. Barnard, William P. Livingston | Summary: As superconducting quantum processors increase in complexity, techniques to overcome constraints on frequency crowding are needed. The recently developed method of laser-annealing provides an effective post-fabrication method to adjust the frequency of superconducting […]


Continue.. Effects of Laser-Annealing on Fixed-Frequency Superconducting Qubits

Prefix Conditioning Unifies Language and Label Supervision

Kavli Affiliate: Xiang Zhang | First 5 Authors: Kuniaki Saito, Kihyuk Sohn, Xiang Zhang, Chun-Liang Li, Chen-Yu Lee | Summary: Vision-language contrastive learning suggests a new learning paradigm by leveraging a large amount of image-caption-pair data. The caption supervision excels at providing wide coverage in vocabulary that enables strong zero-shot image recognition performance. On the […]


Continue.. Prefix Conditioning Unifies Language and Label Supervision

A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

Kavli Affiliate: Xiang Zhang | First 5 Authors: Puyuan Liu, Xiang Zhang, Lili Mou, , | Summary: Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation. In previous work, researchers have developed various approaches to improve the ROUGE […]


Continue.. A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

Kavli Affiliate: Xiang Zhang | First 5 Authors: Puyuan Liu, Xiang Zhang, Lili Mou, , | Summary: Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation. In previous work, researchers have developed various approaches to improve the ROUGE […]


Continue.. A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

On Consistency in Graph Neural Network Interpretation

Kavli Affiliate: Xiang Zhang | First 5 Authors: Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang Wang, | Summary: Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, like nodes or edges, that the target GNN relies upon for making […]


Continue.. On Consistency in Graph Neural Network Interpretation