Results 61 to 70 of about 1,346,527 (187)
Generating Compressed Counterfactual Hard Negative Samples for Graph Contrastive Learning
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT Graph contrastive learning (GCL) relies on acquiring high‐quality positive and negative samples to learn the structural semantics of the input graph. Previous approaches typically sampled negative samples from the same training batch or an irrelevant external graph.
Haoran Yang +7 more
wiley +1 more source
Hybrid Graph Heuristics within a Hyper-heuristic Approach to Exam Timetabling Problems [PDF]
, 2004 This paper is concerned with the hybridization of two graph coloring heuristics (Saturation Degree and Largest Degree), and their application within a hyperheuristic for exam timetabling problems.
Edmund Burke +7 more
core
AlgorithmsThis study introduces a novel train-and-test approach referred to as apprenticeship learning (AL) for generating selection hyper-heuristics to solve the Quadratic Unconstrained Binary Optimisation (QUBO) problem.
Jack Cakebread +4 more
doaj +1 more source
Sub‐optimal Internet of Thing devices deployment using branch and bound method
IET Networks, EarlyView.The main contributions of this paper are (1) IoT network deployment problem formation as MILP problem to optimise the transmission among network nodes, and (2) New BB method with a machine learning function to reduce the computational complexity. Abstract The Internet of Thing (IoT) network deployments are widely investigated in 4G and 5G systems and ...
Haesik Kim
wiley +1 more source
British Journal of Learning Disabilities, EarlyView.ABSTRACT Background People with learning disabilities often face significant challenges in understanding health information. Pictorial supports are widely assumed to improve communication for people with learning disabilities, yet little research examines how visual communication can be effectively designed for this group.
Alison Drewett +5 more
wiley +1 more source
Hyper-heuristic online learning for self-assembling swarm robots
, 2018 © Springer International Publishing AG, part of Springer Nature 2018. A robot swarm is a solution for difficult and large scale tasks. However, controlling and coordinating a swarm of robots is challenging, because of the complexity and uncertainty of ...
S Yu (7291433) +3 more
core +1 more source
CUSTOMHyS: Customising Optimisation Metaheuristics via Hyper-heuristic Search
SoftwareX, 2020 There is a colourful palette of metaheuristics for solving continuous optimisation problems in the literature. Unfortunately, it is not easy to pick a suitable one for a specific practical scenario. Moreover, oftentimes the selected metaheuristic must be
Jorge M. Cruz-Duarte +4 more
doaj +1 more source
Hierarchical Differentiable Fluid Simulation
Computer Graphics Forum, EarlyView.We introduce a two‐step algorithm that significantly reduces memory usage for solving control problems using differentiable fluid simulation techniques: our method first optimizes for bulk forces at reduced resolution, then refines local details over sub‐domains while maintaining differentiability. In trading runtime for memory, it enables optimization
Xiangyu Kong +4 more
wiley +1 more source
IEEE AccessThe urgent demand to reduce carbon emissions due to global warming has driven innovative approaches in cloud computing. This paper introduces the Hyper-Heuristic for Cloud Scheduling Problems (HHCSP), a hyper-heuristic designed to optimize tasks in cloud
Vinicius Renan De Carvalho +1 more
doaj +1 more source
Hyper-Heuristic Approach for Improving Marker Efficiency
AUTEX Research Journal, 2018 Marker planning is an optimization arrangement problem, where a set of cutting parts need to be placed on a thin paper without overlapping to create a marker – an exact diagram of cutting parts that will be cut from a single spread.
Domović Daniel +2 more
doaj +1 more source