skip to main content
Explore Scholarly Publications and Datasets in the NSF-PAR

  • Home
  • Search Results
  • Page 1 of 59

Search for: All records

Creators/Authors contains: "Chen, C."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. ; ; ; ; ; ; ( , The 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE))
    Free, publicly-accessible full text available August 19, 2022
  2. ; ; ; ; ; ( , International Conference on High Performance Computing 2021)
    Free, publicly-accessible full text available June 17, 2022
  3. ; ; ; ; ; ; ; ; ; ; et al ( , Physical Review X)
    Free, publicly-accessible full text available November 1, 2022
  4. ; ; ; ; ; ( , Proceedings of the 43rd European Conference on Information Retrieval (ECIR 2021))
    Recent work on Question Answering (QA) and Conversational QA (ConvQA) emphasizes the role of retrieval: a system first retrieves evidence from a large collection and then extracts answers. This open-retrieval setting typically assumes that each question is answerable by a single span of text within a particular passage (a span answer). The supervision signal is thus derived from whether or not the system can recover an exact match of this ground-truth answer span from the retrieved passages. This method is referred to as span-match weak supervision. However, information-seeking conversations are challenging for this span-match method since long answers, especially freeformmore »answers, are not necessarily strict spans of any passage. Therefore, we introduce a learned weak supervision approach that can identify a paraphrased span of the known answer in a passage. Our experiments on QuAC and CoQA datasets show that although a span-match weak supervisor can handle conversations with span answers, it is not sufficient for freeform answers generated by people. We further demonstrate that our method is more flexible since it can handle both span answers and freeform answers. In particular, our method outperforms the span-match method on conversations with freeform answers, and it can be more powerful when combined with the span-match method. We also conduct in-depth analyses to show more insights on open-retrieval ConvQA under a weak supervision setting.« less
    Full Text Available 
  5. ; ; ; ; ( , ICLR)
    Accepted Manuscript Full Text Available
  6. ; ; ; ; ; ; ; ; ; ; et al ( , PLOS genetics)
    Free, publicly-accessible full text available July 1, 2022
  7. ; ; ; ; ; ( , Monthly Notices of the Royal Astronomical Society)
    ABSTRACT Of all the factors that influence star formation, magnetic fields are perhaps the least well understood. The goal of this paper is to characterize the 3D magnetic field properties of nearby molecular clouds through various methods of statistically analysing maps of polarized dust emission. Our study focuses on nine clouds, with data taken from the Planck Sky Survey as well as data from the Balloon-borne Large Aperture Submillimeter Telescope for Polarimetry observations of Vela C. We compare the distributions of polarization fraction (p), dispersion in polarization angles ($\mathcal {S}$), and hydrogen column density (NH) for each of our targeted clouds.more »To broaden the scope of our analysis, we compare the distributions of our clouds’ polarization observables with measurements from synthetic polarization maps generated from numerical simulations. We also use the distribution of polarization fraction measurements to estimate the inclination angle of each cloud’s cloud-scale magnetic field. We obtain a range of inclination angles associated with our clouds, varying from 16○ to 69○. We establish inverse correlations between p and both $\mathcal {S}$ and NH in almost every cloud, but we are unable to establish a statistically robust $\mathcal {S}$ versus NH trend. By comparing the results of these different statistical analysis techniques, we are able to propose a more comprehensive view of each cloud’s 3D magnetic field properties. These detailed cloud analyses will be useful in the continued studies of cloud-scale magnetic fields and the ways in which they affect star formation within these molecular clouds.« less
    Full Text Available 
  8. ; ; ; ; ; ; ; ; ; ; et al ( , Physical Review Letters)
    Free, publicly-accessible full text available December 1, 2022
  9. ; ; ( , 34th Conference on Neural Information Processing Systems)
    Federated learning allows multiple users to collaboratively train a shared classifica- tion model while preserving data privacy. This approach, where model updates are aggregated by a central server, was shown to be vulnerable to poisoning backdoor attacks: a malicious user can alter the shared model to arbitrarily classify specific inputs from a given class. In this paper, we analyze the effects of backdoor attacks on federated meta-learning, where users train a model that can be adapted to dif- ferent sets of output classes using only a few examples. While the ability to adapt could, in principle, make federated learning frameworksmore »more robust to backdoor attacks (when new training examples are benign), we find that even 1-shot attacks can be very successful and persist after additional training. To address these vulner- abilities, we propose a defense mechanism inspired by matching networks, where the class of an input is predicted from the similarity of its features with a support set of labeled examples. By removing the decision logic from the model shared with the federation, success and persistence of backdoor attacks are greatly reduced.« less
    Accepted Manuscript Full Text Available
  10. ; ; ; ; ( , International Conference on Learning Representations (ICLRR))
    url: https://openreview.net/pdf?id=LGgdb4TS4Z
    Accepted Manuscript Full Text Available