367 citations · 1.3k across the 62 of their papers we have counts for
24 papers · 1 filter
Solving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential Transfer
Tingyang Wei, Haofeng Wu, Ananda Phan Iman +3
Applying knowledge transfer across multiple optimization tasks, multitask optimization (MTO) emerges as a promising approach to solving synergistic optimization tasks simultaneousl…
Interpretable and Fair Generalized Additive Neural Networks via Multi-objective Learning
Ziming Wang, Changwu Huang, Ke Tang +2
Interpretability and fairness are two of the most emphasized dimensions in trustworthy artificial intelligence (AI). Various explainable AI methods have been introduced to improve…
PETA:Parameter-Efficient Test-Time Adaptation for Virtual Screening
Jia-Qi Lin, Yinghua Yao, Chang-Dong Wang +2
Accurately ranking active ligands for a target protein pocket from massive chemical libraries remains a central challenge in virtual screening. DrugCLIP and its recent extensions s…
Co-Learning Bayesian Optimization
Zhendong Guo, Yew-Soon Ong, Tiantian He +1
Bayesian optimization (BO) is well known to be sample-efficient for solving black-box problems. However, the BO algorithms can sometimes get stuck in suboptimal solutions even with…
Prompt Evolution for Generative AI: A Classifier-Guided Approach
Melvin Wong, Yew-Soon Ong, Abhishek Gupta +2
Synthesis of digital artifacts conditioned on user prompts has become an important paradigm facilitating an explosion of use cases with generative AI. However, such models often fa…
Bayesian Federated Learning: A Survey
Longbing Cao, Hui Chen, Xuhui Fan +3
Federated learning (FL) demonstrates its advantages in integrating distributed infrastructure, communication, computing and learning in a privacy-preserving manner. However, the ro…
LSA-PINN: Linear Boundary Connectivity Loss for Solving PDEs on Complex Geometry
Jian Cheng Wong, Pao-Hsiung Chiu, Chinchun Ooi +2
We present a novel loss formulation for efficient learning of complex dynamics from governing physics, typically described by partial differential equations (PDEs), using physics-i…
Policy Dispersion in Non-Markovian Environment
Bohao Qu, Xiaofeng Cao, Jielong Yang +4
Markov Decision Process (MDP) presents a mathematical framework to formulate the learning processes of agents in reinforcement learning. MDP is limited by the Markovian assumption…
Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learning
Tiantian He, Haicang Zhou, Yew-Soon Ong +1
Graph attention networks (GATs) are powerful tools for analyzing graph data from various real-world scenarios. To learn representations for downstream tasks, GATs generally attend…
Jacobian Granger Causal Neural Networks for Analysis of Stationary and Nonstationary Data
Suryadi, Yew-Soon Ong, Lock Yue Chew
Granger causality is a commonly used method for uncovering information flow and dependencies in a time series. Here we introduce JGC (Jacobian Granger Causality), a neural network-…
How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?
Alvin Chan, Yew-Soon Ong, Clement Tan
Model robustness is vital for the reliable deployment of machine learning models in real-world applications. Recent studies have shown that data augmentation can result in model ov…
CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
Pao-Hsiung Chiu, Jian Cheng Wong, Chinchun Ooi +2
In this study, novel physics-informed neural network (PINN) methods for coupling neighboring support points and their derivative terms which are obtained by automatic differentiati…
Adversary Agnostic Robust Deep Reinforcement Learning
Xinghua Qu, Yew-Soon Ong, Abhishek Gupta +1
Deep reinforcement learning (DRL) policies have been shown to be deceived by perturbations (e.g., random noise or intensional adversarial attacks) on state observations that appear…
Heterogeneous Representation Learning: A Review
Joey Tianyi Zhou, Xi Peng, Yew-Soon Ong
The real-world data usually exhibits heterogeneous properties such as modalities, views, or resources, which brings some unique challenges wherein the key is Heterogeneous Represen…
What it Thinks is Important is Important: Robustness Transfers through Input Gradients
Alvin Chan, Yi Tay, Yew-Soon Ong
Adversarial perturbations are imperceptible changes to input pixels that can change the prediction of deep learning models. Learned weights of models robust to such perturbations a…
A Multi-Task Gradient Descent Method for Multi-Label Learning
Lu Bai, Yew-Soon Ong, Tiantian He +1
Multi-label learning studies the problem where an instance is associated with a set of labels. By treating single-label learning problem as one task, the multi-label learning probl…
Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy
Xinghua Qu, Zhu Sun, Yew-Soon Ong +2
Recent studies have revealed that neural network-based policies can be easily fooled by adversarial examples. However, while most prior works analyze the effects of perturbing ever…
DEVDAN: Deep Evolving Denoising Autoencoder
Andri Ashfahani, Mahardhika Pratama, Edwin Lughofer +1
The Denoising Autoencoder (DAE) enhances the flexibility of the data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic des…
Automatic Construction of Multi-layer Perceptron Network from Streaming Examples
Mahardhika Pratama, Choiru Za'in, Andri Ashfahani +2
Autonomous construction of deep neural network (DNNs) is desired for data streams because it potentially offers two advantages: proper model's capacity and quick reaction to drift…
Ockham's Razor in Memetic Computing: Three Stage Optimal Memetic Exploration
G. Iacca, F. Neri, E. Mininno +2
Memetic Computing is a subject in computer science which considers complex structures as the combination of simple agents, memes, whose evolutionary interactions lead to intelligen…
Autonomous Deep Learning: Incremental Learning of Denoising Autoencoder for Evolving Data Streams
Mahardhika Pratama, Andri Ashfahani, Yew Soon Ong +2
The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples. None…
Adaptive Subgradient Methods for Online AUC Maximization
Yi Ding, Peilin Zhao, Steven C. H. Hoi +1
Learning for maximizing AUC performance is an important research problem in Machine Learning and Artificial Intelligence. Unlike traditional batch learning methods for maximizing A…
Discovering Support and Affiliated Features from Very High Dimensions
Yiteng Zhai, Mingkui Tan, Ivor Tsang +1
In this paper, a novel learning paradigm is presented to automatically identify groups of informative and correlated features from very high dimensions. Specifically, we explicitly…
Transductive Ordinal Regression
Chun-Wei Seah, Ivor W. Tsang, Yew-Soon Ong
Ordinal regression is commonly formulated as a multi-class problem with ordinal constraints. The challenge of designing accurate classifiers for ordinal regression generally increa…