English

Unfolding Projection-free SDP Relaxation of Binary Graph Classifier via GDPA Linearization

Machine Learning 2021-09-13 v1

Abstract

Algorithm unfolding creates an interpretable and parsimonious neural network architecture by implementing each iteration of a model-based algorithm as a neural layer. However, unfolding a proximal splitting algorithm with a positive semi-definite (PSD) cone projection operator per iteration is expensive, due to the required full matrix eigen-decomposition. In this paper, leveraging a recent linear algebraic theorem called Gershgorin disc perfect alignment (GDPA), we unroll a projection-free algorithm for semi-definite programming relaxation (SDR) of a binary graph classifier, where the PSD cone constraint is replaced by a set of "tightest possible" linear constraints per iteration. As a result, each iteration only requires computing a linear program (LP) and one extreme eigenvector. Inside the unrolled network, we optimize parameters via stochastic gradient descent (SGD) that determine graph edge weights in two ways: i) a metric matrix that computes feature distances, and ii) a sparse weight matrix computed via local linear embedding (LLE). Experimental results show that our unrolled network outperformed pure model-based graph classifiers, and achieved comparable performance to pure data-driven networks but using far fewer parameters.

Keywords

Cite

@article{arxiv.2109.04697,
  title  = {Unfolding Projection-free SDP Relaxation of Binary Graph Classifier via GDPA Linearization},
  author = {Cheng Yang and Gene Cheung and Wai-tian Tan and Guangtao Zhai},
  journal= {arXiv preprint arXiv:2109.04697},
  year   = {2021}
}
R2 v1 2026-06-24T05:51:02.858Z