Search Results for author:
Found 79 papers, 20 papers with code
S4TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles
To effectively assess the risks prevailing in the vicinity of AVs in social interactive traffic scenarios and achieve safe autonomous driving, this article proposes a social-suitable and safety-sensitive trajectory planning (S4TP) framework.
Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization
Large Language Models exhibit robust problem-solving capabilities for diverse tasks.
Label Informed Contrastive Pretraining for Node Importance Estimation on Knowledge Graphs
Considering the NIE problem, LICAP adopts a novel sampling strategy called top nodes preferred hierarchical sampling to first group all interested nodes into a top bin and a non-top bin based on node importance scores, and then divide the nodes within top bin into several finer bins also based on the scores.
Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey
Specifically, we systematically summarize recent advancements in relevant algorithms and identify three primary research directions: EA-assisted optimization of RL, RL-assisted optimization of EA, and synergistic optimization of EA and RL.
Divide-and-Conquer Strategy for Large-Scale Dynamic Bayesian Network Structure Learning
Our approach significantly improves the scalability and accuracy of 2-TBN structure learning.
Pointer Networks Trained Better via Evolutionary Algorithms
With this advantage, this paper is able to at the first time report the results of solving 1000-dimensional TSPs by training a PtrNet on the same dimensionality, which strongly suggests that scaling up the training instances is in need to improve the performance of PtrNet on solving higher-dimensional COPs.
Large Language Models as Evolutionary Optimizers
Specifically, in each generation of the evolutionary search, LMEA instructs the LLM to select parent solutions from current population, and perform crossover and mutation to generate offspring solutions.
TF-DCon: Leveraging Large Language Models (LLMs) to Empower Training-Free Dataset Condensation for Content-Based Recommendation
Notably, the condensation paradigm of this method is forward and free from iterative optimization on the synthesized dataset.
Migrant Resettlement by Evolutionary Multi-objective Optimization
In this paper, we propose a new framework MR-EMO based on Evolutionary Multi-objective Optimization, which reformulates Migrant Resettlement as a bi-objective optimization problem that maximizes the expected number of employed migrants and minimizes the number of dispatched migrants simultaneously, and employs a Multi-Objective Evolutionary Algorithm (MOEA) to solve the bi-objective problem.
Dataset Condensation for Recommendation
However, applying existing approaches to condense recommendation datasets is impractical due to following challenges: (i) sampling-based methods are inadequate in addressing the long-tailed distribution problem; (ii) synthesizing-based methods are not applicable due to discreteness of interactions and large size of recommendation datasets; (iii) neither of them fail to address the specific issue in recommendation of false negative items, where items with potential user interest are incorrectly sampled as negatives owing to insufficient exposure.
Enhancing Graph Collaborative Filtering via Uniformly Co-Clustered Intent Modeling
To model the compatibility between user intents and item properties, we design the user-item co-clustering module, maximizing the mutual information of co-clusters of users and items.
Neural Influence Estimator: Towards Real-time Solutions to Influence Blocking Maximization
Moreover, given a real-time constraint of one minute, the NIE-based method can solve IBM problems with up to hundreds of thousands of nodes, which is at least one order of magnitude larger than what can be solved by existing methods.
Chance-Constrained Multiple-Choice Knapsack Problem: Model, Algorithms, and Applications
In particular, we focus on the practical scenario of CCMCKP, where the probability distributions of random weights are unknown but only sample data is available.
Statistical Tests for Replacing Human Decision Makers with Algorithms
This paper proposes a statistical framework with which artificial intelligence can improve human decision making.
Perturbation-Based Two-Stage Multi-Domain Active Learning
Active Learning (AL) presents an encouraging solution to this issue by annotating a smaller number of highly informative instances, thereby reducing the labeling effort.
Large Language Models can be Guided to Evade AI-Generated Text Detection
Large language models (LLMs) have shown remarkable performance in various tasks and have been extensively utilized by the public.
Multi-Domain Learning From Insufficient Annotations
Multi-domain learning (MDL) refers to simultaneously constructing a model or a set of models on datasets collected from different domains.
MetaUE: Model-based Meta-learning for Underwater Image Enhancement
The meta-learning strategy is used to obtain a pre-trained model on the synthetic underwater dataset, which contains different types of degradation to cover the various underwater environments.
Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend
Our comprehensive experiments reveal that in approximately 90\% of cases, word-level attacks lead to the generation of examples where the frequency of $n$-grams decreases, a tendency we term as the $n$-gram Frequency Descend ($n$-FD).
Enabling surrogate-assisted evolutionary reinforcement learning via policy embedding
The training process is accelerated up to 7x on tested games, comparing to its counterpart without the surrogate and PE.
Reliable Robustness Evaluation via Automatically Constructed Attack Ensembles
Attack Ensemble (AE), which combines multiple attacks together, provides a reliable way to evaluate adversarial robustness.
Causality-driven Hierarchical Structure Discovery for Reinforcement Learning
To address this issue, we propose CDHRL, a causality-driven hierarchical reinforcement learning framework, leveraging a causality-driven discovery instead of a randomness-driven exploration to effectively build high-quality hierarchical structures in complicated environments.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
How Good Is Neural Combinatorial Optimization? A Systematic Evaluation on the Traveling Salesman Problem
Hopefully, this work would help with a better understanding of the strengths and weaknesses of NCO and provide a comprehensive evaluation protocol for further benchmarking NCO approaches in comparison to other approaches.
Disentangled Contrastive Learning for Social Recommendation
In this work, to address such limitation, we propose a novel Disentangled contrastive learning framework for social Recommendations DcRec.
Experience of the COVID-19 pandemic in Wuhan leads to a lasting increase in social distancing
On 11th Jan 2020, the first COVID-19 related death was confirmed in Wuhan, Hubei.
GANDSE: Generative Adversarial Network based Design Space Exploration for Neural Network Accelerator Design
To improve the design quality while saving the cost, design automation for neural network accelerators was proposed, where design space exploration algorithms are used to automatically search the optimized accelerator design within a design space.
Defending Adversarial Examples by Negative Correlation Ensemble
The security issues in DNNs, such as adversarial examples, have attracted much attention.
Saliency Attack: Towards Imperceptible Black-box Adversarial Attack
In this paper, we propose to restrict the perturbations to a small salient region to generate adversarial examples that can hardly be perceived.
Fast Multi-grid Methods for Minimizing Curvature Energy
In this paper, we propose fast multi-grid algorithms for minimizing both mean curvature and Gaussian curvature energy functionals without sacrificing accuracy for efficiency.
Training Quantized Deep Neural Networks via Cooperative Coevolution
This work considers a challenging Deep Neural Network(DNN) quantization task that seeks to train quantized DNNs without involving any full-precision operations.
Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization
The field of adversarial textual attack has significantly grown over the last few years, where the commonly considered objective is to craft adversarial examples (AEs) that can successfully fool the target model.
Imperceptible Black-box Attack via Refining in Salient Region
To address this issue, in this paper we propose to use segmentation priors for black-box attacks such that the perturbations are limited in the salient region.
Learning Controllable Elements Oriented Representations for Reinforcement Learning
Deep Reinforcement Learning (deep RL) has been successfully applied to solve various decision-making problems in recent years.
An AI-assisted Economic Model of Endogenous Mobility and Infectious Diseases: The Case of COVID-19 in the United States
We build a deep-learning-based SEIR-AIM model integrating the classical Susceptible-Exposed-Infectious-Removed epidemiology model with forecast modules of infection, community mobility, and unemployment.
Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack
Over the past few years, various word-level textual attack approaches have been proposed to reveal the vulnerability of deep neural networks used in natural language processing.
Crypto Wash Trading
We introduce systematic tests exploiting robust statistical and behavioral patterns in trading to detect fake transactions on 29 cryptocurrency exchanges.
Deep Sequence Modeling: Development and Applications in Asset Pricing
We predict asset returns and measure risk premia using a prominent technique from artificial intelligence -- deep sequence modeling.
Active Reinforcement Learning over MDPs
This paper proposes a framework of Active Reinforcement Learning (ARL) over MDPs to improve generalization efficiency in a limited resource by instance selection.
Multi-Domain Active Learning: Literature Review and Comparative Study
Active learning (AL) can be utilized in MDL to reduce the labeling effort by only using the most informative data.
Robust Dynamic Network Embedding via Ensembles
It is natural to ask if existing DNE methods can perform well for an input dynamic network without smooth changes.
Multi-objective Evolutionary Algorithms are Generally Good: Maximizing Monotone Submodular Functions over Sequences
Evolutionary algorithms (EAs) are general-purpose optimization algorithms, inspired by natural evolution.
A New Knowledge Gradient-based Method for Constrained Bayesian Optimization
An unbiased estimator of the gradient of the new acquisition function is derived to implement the $c-\rm{KG}$ approach.
A Survey on Neural Network Interpretability
Along with the great success of deep neural networks, there is also growing concern about their black-box nature.
Memetic Search for Vehicle Routing with Simultaneous Pickup-Delivery and Time Windows
The Vehicle Routing Problem with Simultaneous Pickup-Delivery and Time Windows (VRPSPDTW) has attracted much research interest in the last decade, due to its wide application in modern logistics.
Interpreting Deep Learning Model Using Rule-based Method
For global explanation, frequency-based and out-of-bag based methods are proposed to extract important features in the neural network decision.
Evolutionary Reinforcement Learning via Cooperative Coevolutionary Negatively Correlated Search
Evolutionary algorithms (EAs) have been successfully applied to optimize the policies for Reinforcement Learning (RL) tasks due to their exploration ability.
GloDyNE: Global Topology Preserving Dynamic Network Embedding
The main and common objective of Dynamic Network Embedding (DNE) is to efficiently update node embeddings while preserving network topology at each time step.
Few-shots Parallel Algorithm Portfolio Construction via Co-evolution
In the context of heuristic search, such a paradigm could be implemented as configuring the parameters of a parallel algorithm portfolio (PAP) based on a set of training problem instances, which is often referred to as PAP construction.
Impact of Temperature and Relative Humidity on the Transmission of COVID-19: A Modeling Study in China and the United States
Primary outcome measures: Regression analysis of the impact of temperature and relative humidity on the effective reproductive number (R value).
Optimal Stochastic and Online Learning with Individual Iterates
In this paper, we propose a theoretically sound strategy to select an individual iterate of the vanilla SCMD, which is able to achieve optimal rates for both convex and strongly convex problems in a non-smooth learning setting.
Explicit Planning for Efficient Exploration in Reinforcement Learning
We argue that explicit planning for exploration can help alleviate such a problem, and propose a Value Iteration for Exploration Cost (VIEC) algorithm which computes the optimal exploration scheme by solving an augmented MDP.
On Performance Estimation in Automatic Algorithm Configuration
Over the last decade, research on automated parameter tuning, often referred to as automatic algorithm configuration (AAC), has made significant progress.
Parallel Exploration via Negatively Correlated Search
Empirical results show that the significant advantages of NCS over the compared state-of-the-art methods can be highly owed to the effective parallel exploration ability.
Competitive Coevolution as an Adversarial Approach to Dynamic Optimization
In this paper, a new framework of employing EAs in the context of dynamic optimization is explored.
On the Robustness of Median Sampling in Noisy Evolutionary Optimization
Sampling is a popular strategy, which evaluates the objective a couple of times, and employs the mean of these evaluation results as an estimate of the objective value.
DynWalks: Global Topology and Recent Changes Awareness Dynamic Network Embedding
Dynamic network embedding aims to learn low dimensional embeddings for unseen and seen nodes by using any currently available snapshots of a dynamic network.
AlphaStock: A Buying-Winners-and-Selling-Losers Investment Strategy using Interpretable Deep Reinforcement Attention Networks
Recent years have witnessed the successful marriage of finance innovations and AI techniques in various finance applications including quantitative trading (QT).
Running Time Analysis of the (1+1)-EA for Robust Linear Optimization
Evolutionary algorithms (EAs) have found many successful real-world applications, where the optimization problems are often subject to a wide range of uncertainties.
Decision Making with Machine Learning and ROC Curves
Our theoretical discussion is illustrated in the context of a large data set of pregnancy outcomes and doctor diagnosis from the Pre-Pregnancy Checkups of reproductive age couples in Henan Province provided by the Chinese Ministry of Health.
Stochastic Gradient Descent for Nonconvex Learning without Bounded Gradient Assumptions
While the behavior of SGD is well understood in the convex learning setting, the existing theoretical results for SGD applied to nonconvex objective functions are far from mature.
A Parallel Divide-and-Conquer based Evolutionary Algorithm for Large-scale Optimization
Large-scale optimization problems that involve thousands of decision variables have extensively arisen from various industrial areas.
Stochastic Composite Mirror Descent: Optimal Bounds with High Probabilities
We apply the derived computational error bounds to study the generalization performance of multi-pass stochastic gradient descent (SGD) in a non-parametric setting.
Attributed Network Embedding for Incomplete Attributed Networks
Attributed networks are ubiquitous since a network often comes with auxiliary attribute information e. g. a social network with user profiles.
Maximizing Monotone DR-submodular Continuous Functions by Derivative-free Optimization
Under a convex polytope constraint, we prove that LDGM can achieve a $(1-e^{-\beta}-\epsilon)$-approximation guarantee after $O(1/\epsilon)$ iterations, which is the same as the best previous gradient-based algorithm.
Analysis of Noisy Evolutionary Optimization When Sampling Fails
In noisy evolutionary optimization, sampling is a common strategy to deal with noise.
Automatic Construction of Parallel Portfolios via Explicit Instance Grouping
Simultaneously utilizing several complementary solvers is a simple yet effective strategy for solving computationally hard problems.
Subset Selection under Noise
The problem of selecting the best $k$-element subset from a universe is involved in many applications.
Log-normality and Skewness of Estimated State/Action Values in Reinforcement Learning
Under/overestimation of state/action values are harmful for reinforcement learning agents.
Maximizing Submodular or Monotone Approximately Submodular Functions by Multi-objective Evolutionary Algorithms
To provide a general theoretical explanation of the behavior of EAs, it is desirable to study their performance on general classes of combinatorial optimization problems.
Running Time Analysis of the (1+1)-EA for OneMax and LeadingOnes under Bit-wise Noise
We analyze the running time of the (1+1)-EA solving OneMax and LeadingOnes under bit-wise noise for the first time, and derive the ranges of the noise level for polynomial and super-polynomial running time bounds.
Preselection via Classification: A Case Study on Evolutionary Multiobjective Optimization
Finally it uses the classifier to filter the unpromising candidate offspring solutions and choose a promising one from the generated candidate offspring set for each parent solution.
Evolutionary Multitasking for Single-objective Continuous Optimization: Benchmark Problems, Performance Metric, and Baseline Results
In this report, we suggest nine test problems for multi-task single-objective optimization (MTSOO), each of which consists of two single-objective optimization tasks that need to be solved simultaneously.
Experience-based Optimization: A Coevolutionary Approach
The idea behind LiangYi is to promote the population-based solver by training it (with the training module) to improve its performance on those instances (discovered by the sampling module) on which it performs badly, while keeping the good performances obtained by it on previous instances.
An Adaptive Framework to Tune the Coordinate Systems in Evolutionary Algorithms
In the evolutionary computation research community, the performance of most evolutionary algorithms (EAs) depends strongly on their implemented coordinate system.
Concept Drift Adaptation by Exploiting Historical Knowledge
Incremental learning with concept drift has often been tackled by ensemble methods, where models built in the past can be re-trained to attain new models for the current data.
Success Probability of Exploration: a Concrete Analysis of Learning Efficiency
We then provide empirical results to verify our approach, and demonstrate how the success probability of exploration can be used to analyse and predict the behaviours and possible outcomes of exploration, which are the keys to the answer of the important questions of exploration.
High-dimensional Black-box Optimization via Divide and Approximate Conquer
Divide and Conquer (DC) is conceptually well suited to high-dimensional optimization by decomposing a problem into multiple small-scale sub-problems.
Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection
R-CNN style methods are sorts of the state-of-the-art object detection methods, which consist of region proposal generation and deep CNN classification.
Negatively Correlated Search
This paper presents a new EA, namely Negatively Correlated Search (NCS), which maintains multiple individual search processes in parallel and models the search behaviors of individual search processes as probability distributions.
