Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–3 of 3 results for author: Wegman, M N

Searching in archive cs. Search in all archives.
.
  1. arXiv:2306.00262  [pdf, ps, other

    cs.CV cs.LG

    Maximizing Information in Domain-Invariant Representation Improves Transfer Learning

    Authors: Adrian Shuai Li, Elisa Bertino, Xuan-Hong Dang, Ankush Singla, Yuhai Tu, Mark N Wegman

    Abstract: We propose MaxDIRep, a domain adaptation method that improves the decomposition of data representations into domain-independent and domain-dependent components. Existing methods, such as Domain-Separation Networks (DSN), use a weak orthogonality constraint between these components, which can lead to label-relevant features being partially encoded in the domain-dependent representation (DDRep) rath… ▽ More

    Submitted 9 September, 2025; v1 submitted 31 May, 2023; originally announced June 2023.

  2. arXiv:1802.07896  [pdf, ps, other

    cs.AI cs.LG

    L2-Nonexpansive Neural Networks

    Authors: Haifeng Qian, Mark N. Wegman

    Abstract: This paper proposes a class of well-conditioned neural networks in which a unit amount of change in the inputs causes at most a unit amount of change in the outputs or any of the internal layers. We develop the known methodology of controlling Lipschitz constants to realize its full potential in maximizing robustness, with a new regularization scheme for linear layers, new ways to adapt nonlineari… ▽ More

    Submitted 6 February, 2019; v1 submitted 21 February, 2018; originally announced February 2018.

    Journal ref: International Conference on Learning Representations (ICLR), 2019

  3. arXiv:1612.07365  [pdf, ps, other

    cs.SI

    A Proximity Measure using Blink Model

    Authors: Haifeng Qian, Hui Wan, Mark N. Wegman, Luis A. Lastras, Ruchir Puri

    Abstract: This paper proposes a new graph proximity measure. This measure is a derivative of network reliability. By analyzing its properties and comparing it against other proximity measures through graph examples, we demonstrate that it is more consistent with human intuition than competitors. A new deterministic algorithm is developed to approximate this measure with practical complexity. Empirical evalu… ▽ More

    Submitted 21 December, 2016; originally announced December 2016.