On Structuring Hyperspherical Manifold for Probing Novel Biomedical Entities.

Journal: IEEE transactions on pattern analysis and machine intelligence
Published Date:

Abstract

The insufficient high- throughput modeling capability for high-dimensional, multiscale, and nonlinear real-world observations and measurements stands as one of the major impediments for modern science advancements. In this regard, machine learning holds tremendous promise for transforming the fundamental practice of scientific discovery by virtue of its data-driven disposition. With the ever-increasing stream of research data collection, it would be appealing to automate the exploration of patterns and insights from observational data for discovering novel classes of phenotypes and entities. However, in the discipline of biomedical investigation, the cumulative data is intrinsically subjected to non-i.i.d. distribution and severe biases amongst different clusters, inducing disorganization and ambiguity in the learned representation space. To contend with the inherent challenges, in this paper, we present a geometry- constrained probabilistic modeling treatment on hyperspherical manifolds. It firstly parameterizes the approximated posterior of instance- wise embedding as a marginal von MisesFisher distribution to account for the interference of distributional latent shift, and thereafter incorporates a suite of critical inductive biases to organically shape the layout of tailored embedding space. Together, these advancements offer a systematic solution to regularize the uncontrollable risk for unseen class learning and prospecting. Furthermore, we propose a spectral graph-theoretic method to efficiently estimate the number of potential novel classes and endow the prediction with adorable taxonomy adaptability. Through extensive experiments under various settings, we demonstrate the effectiveness and general applicability of the proposed methods in recognizing and structurally phenotyping novel visual concepts.

Authors

  • Jianan Fan
    Analysis and Testing Central Facility, Institutes of Molecular Engineering and Applied Chemistry, Anhui University of Technology, Ma'anshan 243002, China.
  • Dongnan Liu
  • Hang Chang
    Biological Systems and Engineering Division, Lawrence Berkeley National Laboratory, Berkeley, CA, United States.
  • Heng Huang
    Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, USA.
  • Mei Chen
    The First People's Hospital of Longquanyi District, Chengdu, Sichuan Province 610100, China.
  • Weidong Cai
    School of Computer Science, The University of Sydney, Darlington, WA, Australia.

Keywords

No keywords available for this article.