Graph Classification Method Based on Wasserstein Distance
نویسندگان
چکیده
منابع مشابه
Distance-Based Topological Indices and Double graph
Let $G$ be a connected graph, and let $D[G]$ denote the double graph of $G$. In this paper, we first derive closed-form formulas for different distance based topological indices for $D[G]$ in terms of that of $G$. Finally, as illustration examples, for several special kind of graphs, such as, the complete graph, the path, the cycle, etc., the explicit formulas for some distance based topologica...
متن کاملWasserstein Distance Measure Machines
This paper presents a distance-based discriminative framework for learning with probability distributions. Instead of using kernel mean embeddings or generalized radial basis kernels, we introduce embeddings based on dissimilarity of distributions to some reference distributions denoted as templates. Our framework extends the theory of similarity of Balcan et al. (2008) to the population distri...
متن کاملA Fast Proximal Point Method for Wasserstein Distance
Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations such as Sinkhorn distance. However, as we will demonstrate, several important machine learning applications call for the computation of exact...
متن کاملdistance-based topological indices and double graph
let $g$ be a connected graph, and let $d[g]$ denote the double graph of $g$. in this paper, we first derive closed-form formulas for different distance based topological indices for $d[g]$ in terms of that of $g$. finally, as illustration examples, for several special kind of graphs, such as, the complete graph, the path, the cycle, etc., the explicit formulas for some distance based topologica...
متن کاملLattice Fokker-Planck Method Based on Wasserstein Gradient Flows
Abstract A lattice Fokker-Planck method is introduced based upon a variational formulation of the time evolution as a Wasserstein gradient flow within the space of probability densities of the system. Gradient descent directions are efficiently generated by exploiting the link to Langevin dynamics and the parallel-execution capabilities of graphics processing units. This approach can capture al...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Physics: Conference Series
سال: 2021
ISSN: 1742-6588,1742-6596
DOI: 10.1088/1742-6596/1952/2/022018