activity
20172022
most citedEvolutionary Multitasking for Multiobjective Continuous Optimization: Benchmark Problems, Performance Metrics and Baseline Results

134 citations · 210 across the 12 of their papers we have counts for

collaborators

14 papers

cs.LG2022

Multi-task Optimization Based Co-training for Electricity Consumption Prediction

Hui Song, A. K. Qin, Chenggang Yan

Real-world electricity consumption prediction may involve different tasks, e.g., prediction for different time steps ahead or different geo-locations. These tasks are often solved…

cs.LG20221 cited

Sample-Efficient, Exploration-Based Policy Optimisation for Routing Problems

Nasrin Sultana, Jeffrey Chan, Tabinda Sarwar +1

Model-free deep-reinforcement-based learning algorithms have been applied to a range of COPs~\cite{bello2016neural}~\cite{kool2018attention}~\cite{nazari2018reinforcement}. However…

cs.LG20211 cited

ADDS: Adaptive Differentiable Sampling for Robust Multi-Party Learning

Maoguo Gong, Yuan Gao, Yue Wu +1

Distributed multi-party learning provides an effective approach for training a joint model with scattered data under legal and practical constraints. However, due to the quagmire o…

cs.AI20211 cited

Learning Enhanced Optimisation for Routing Problems

Nasrin Sultana, Jeffrey Chan, Tabinda Sarwar +2

Deep learning approaches have shown promising results in solving routing problems. However, there is still a substantial gap in solution quality between machine learning and operat…

cs.NE20211 cited

Evolutionary Ensemble Learning for Multivariate Time Series Prediction

Hui Song, A. K. Qin, Flora D. Salim

Multivariate time series (MTS) prediction plays a key role in many fields such as finance, energy and transport, where each individual time series corresponds to the data collected…

cs.LG2021

Towards Explainable Multi-Party Learning: A Contrastive Knowledge Sharing Framework

Yuan Gao, Jiawei Li, Maoguo Gong +2

Multi-party learning provides solutions for training joint models with decentralized data under legal and practical constraints. However, traditional multi-party learning approache…