Results 11 to 20 of about 112,175 (269)

Node-Feature Convolution for Graph Convolutional Networks [PDF]

Pattern Recognition, 2022
Graph convolutional network (GCN) is an effective neural network model for graph representation learning. However, standard GCN suffers from three main limitations: (1) most real-world graphs have no regular connectivity and node degrees can range from one to hundreds or thousands, (2) neighboring nodes are aggregated with fixed weights, and (3) node ...
Zhang, L., Song, H., Aletras, N., Lu, H.
openaire   +2 more sources

Convolution and concurrency

Mathematical Structures in Computer Science, 2021
AbstractWe show how concurrent quantales and concurrent Kleene algebras arise as convolution algebras of functions from relational structures with two ternary relations that satisfy relational interchange laws into concurrent quantales or Kleene algebras, among others.
James Cranch, Simon Doherty, Georg Struth   +2 more
openaire   +3 more sources

Dynamic Convolution: Attention Over Convolution Kernels [PDF]

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
CVPR 2020 (Oral)
Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen 0001, Lu Yuan, Zicheng Liu 0001   +5 more
openaire   +2 more sources

Convolution in Convolution for Network in Network [PDF]

IEEE Transactions on Neural Networks and Learning Systems, 2018
A method of Convolutional Neural ...
Pang, Yanwei, Sun, Manli, Jiang, Xiaoheng, Li, Xuelong, Pang, YW (reprint author), Tianjin Univ, Sch Elect & Informat Enginnering, Tianjin 300072, Peoples R China.   +4 more
openaire   +4 more sources

Counterpoint By Convolution. [PDF]

CoRR, 2017
Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR ...
Cheng-Zhi Anna Huang, Tim Cooijmans, Adam Roberts, Aaron C. Courville, Douglas Eck   +4 more
openaire   +3 more sources

Convolutional Codes

CoRR, 2020
published
Lieb, Julia, Pinto, Raquel, Rosenthal, Joachim   +2 more
openaire   +3 more sources

Polar Convolution

SIAM Journal on Optimization, 2019
The Moreau envelope is one of the key convexity-preserving functional operations in convex analysis, and it is central to the development and analysis of many approaches for convex optimization. This paper develops the theory for an analogous convolution operation, called the polar envelope, specialized to gauge functions.
Michael P. Friedlander, Ives Macêdo, Ting Kei Pong   +2 more
openaire   +3 more sources

Comb Convolution for Efficient Convolutional Architecture

CoRR, 2019
15 ...
Dandan Li, Yuan Zhou 0006, Shuwei Huo, Sun-Yuan Kung   +3 more
openaire   +2 more sources

Convolution lattices [PDF]

Fuzzy Sets and Systems, 2018
We propose two convolution operations on the set of functions between two bounded lattices and investigate the algebraic structure they constitute, in particular the lattice laws they satisfy. Each of these laws requires the restriction to a specific subset of functions, such as normal, idempotent or convex functions.
Miguel Turullols, Laura de, Bustince Sola, Humberto, Baets, Bernard de   +2 more
openaire   +4 more sources

Generalized convolutions V [PDF]

Studia Mathematica, 1973
This paper is a continuation of part III, ibid. 80, 167-189 (1984; Zbl 0561.60019). It deals with generalized convolution algebras (\({\mathcal P},\circ)\), i.e. \({\mathcal P}\) is the set of all probability measures on the positive half-line and ``\(\circ ''\) is a generalized convolution of measures from \({\mathcal P}\).
openaire   +7 more sources