Search Results for author: Xi Lin

Found 59 papers, 20 papers with code

IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning

no code implementations4 Feb 2025 Quan Zhang, Yuxin Qi, Xi Tang, Jinwei Fang, Xi Lin, Ke Zhang, Chun Yuan

There are two main challenges in applying SAM to image manipulation detection: a) reliance on manual prompts, and b) the difficulty of single-view information in supporting cross-dataset generalization.

Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond

2 code implementations19 Jan 2025 WeiYu Chen, Xiaoyuan Zhang, Baijiong Lin, Xi Lin, Han Zhao, Qingfu Zhang, James T. Kwok

Multi-objective optimization (MOO) in deep learning aims to simultaneously optimize multiple conflicting objectives, a challenge frequently encountered in areas like multi-task learning and multi-criteria learning.

Deep Learning Multi-Task Learning +1

MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework

no code implementations13 Jan 2025 Ping Guo, Cheng Gong, Xi Lin, Fei Liu, Zhichao Lu, Qingfu Zhang, Zhenkun Wang

Crafting adversarial examples is crucial for evaluating and enhancing the robustness of Deep Neural Networks (DNNs), presenting a challenge equivalent to maximizing a non-differentiable 0-1 loss function.

Adversarial Attack

CoEvo: Continual Evolution of Symbolic Solutions Using Large Language Models

1 code implementation25 Dec 2024 Ping Guo, Qingfu Zhang, Xi Lin

We propose a novel framework that utilizes LLMs in an evolutionary search methodology, augmented by a dynamic knowledge library that integrates and refines insights in an \textit{open-ended manner}.

Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer

1 code implementation10 Dec 2024 Ke Xue, Ruo-Tong Chen, Xi Lin, Yunqi Shi, Shixiong Kai, Siyuan Xu, Chao Qian

In modern chip design, placement aims at placing millions of circuit modules, which is an essential step that significantly influences power, performance, and area (PPA) metrics.

reinforcement-learning Reinforcement Learning +1

VPBSD:Vessel-Pattern-Based Semi-Supervised Distillation for Efficient 3D Microscopic Cerebrovascular Segmentation

no code implementations14 Nov 2024 Xi Lin, Shixuan Zhao, Xinxu Wei, Amir Shmuel, YongJie Li

In the knowledge distillation stage, the codebook facilitates the transfer of rich knowledge from a heterogeneous teacher model to a student model, while the semi-supervised approach further enhances the student model's exposure to diverse learning samples.

Brain Segmentation Knowledge Distillation +1

Multi-objective Evolution of Heuristic Using Large Language Model

no code implementations25 Sep 2024 Shunyu Yao, Fei Liu, Xi Lin, Zhichao Lu, Zhenkun Wang, Qingfu Zhang

We propose the first LLM-based multi-objective heuristic search framework, Multi-objective Evolution of Heuristic (MEoH), which integrates LLMs in a zero-shot manner to generate a non-dominated set of heuristics to meet multiple design criteria.

Combinatorial Optimization Language Modeling +3

Retinal Vessel Segmentation with Deep Graph and Capsule Reasoning

no code implementations17 Sep 2024 Xinxu Wei, Xi Lin, Haiyun Liu, Shixuan Zhao, YongJie Li

Effective retinal vessel segmentation requires a sophisticated integration of global contextual awareness and local vessel continuity.

Graph Attention Image Segmentation +3

LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch

1 code implementation4 Sep 2024 Xiaoyuan Zhang, Liang Zhao, Yingying Yu, Xi Lin, Yifan Chen, Han Zhao, Qingfu Zhang

Multiobjective optimization problems (MOPs) are prevalent in machine learning, with applications in multi-task learning, learning under fairness or robustness constraints, etc.

Evolutionary Algorithms Fairness +2

Decoupled Video Generation with Chain of Training-free Diffusion Model Experts

no code implementations24 Aug 2024 Wenhao Li, Yichao Cao, Xiu Su, Xi Lin, Shan You, Mingkai Zheng, Yi Chen, Chang Xu

It can generate high-quality videos with chain of off-the-shelf diffusion model experts, each expert responsible for a decoupled subtask.

Denoising Video Generation

Causality-Inspired Models for Financial Time Series Forecasting

no code implementations19 Aug 2024 Daniel Cunha Oliveira, Yutong Lu, Xi Lin, Mihai Cucuringu, Andre Fujita

To the best of our knowledge, this is the first study to conduct a comprehensive comparative analysis among state-of-the-art causal discovery algorithms, benchmarked against non-causal feature selection techniques, in the application of forecasting asset returns.

Causal Discovery feature selection +2

Understanding the Importance of Evolutionary Search in Automated Heuristic Design with Large Language Models

no code implementations15 Jul 2024 Rui Zhang, Fei Liu, Xi Lin, Zhenkun Wang, Zhichao Lu, Qingfu Zhang

Automated heuristic design (AHD) has gained considerable attention for its potential to automate the development of effective heuristics.

OpticGAI: Generative AI-aided Deep Reinforcement Learning for Optical Networks Optimization

no code implementations22 Jun 2024 Siyuan Li, Xi Lin, Yaju Liu, Gaolei Li, Jianhua Li

Furthermore, we assess the performance of OpticGAI on two NP-hard optical network problems, Routing and Wavelength Assignment (RWA) and dynamic Routing, Modulation, and Spectrum Allocation (RMSA), to show the feasibility of the AI-generated policy paradigm.

Blocking Deep Reinforcement Learning

Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization

no code implementations30 May 2024 Xi Lin, Yilu Liu, Xiaoyuan Zhang, Fei Liu, Zhenkun Wang, Qingfu Zhang

Existing optimization methods often focus on finding a set of Pareto solutions with different optimal trade-offs among the objectives.

Prompt Learning for Generalized Vehicle Routing

1 code implementation20 May 2024 Fei Liu, Xi Lin, Weiduo Liao, Zhenkun Wang, Qingfu Zhang, Xialiang Tong, Mingxuan Yuan

To be concrete, we propose a novel prompt learning method to facilitate fast zero-shot adaptation of a pre-trained model to solve routing problem instances from different distributions.

Combinatorial Optimization Zero-shot Generalization

Trustworthy AI-Generative Content in Intelligent 6G Network: Adversarial, Privacy, and Fairness

no code implementations9 May 2024 Siyuan Li, Xi Lin, Yaju Liu, Jianhua Li

We believe that TrustGAIN is a necessary paradigm for intelligent and trustworthy 6G networks to support AIGC services, ensuring the security, privacy, and fairness of AIGC network services.

Fairness

Multi-Agent RL-Based Industrial AIGC Service Offloading over Wireless Edge Networks

no code implementations5 May 2024 Siyuan Li, Xi Lin, Hansong Xu, Kun Hua, Xiaomin Jin, Gaolei Li, Jianhua Li

In this paper, we focus on the edge optimization of AIGC task execution and propose GMEL, a generative model-driven industrial AIGC collaborative edge learning framework.

Few-Shot Learning Multi-agent Reinforcement Learning

Instance-Conditioned Adaptation for Large-scale Generalization of Neural Combinatorial Optimization

no code implementations3 May 2024 Changliang Zhou, Xi Lin, Zhenkun Wang, Xialiang Tong, Mingxuan Yuan, Qingfu Zhang

The neural combinatorial optimization (NCO) approach has shown great potential for solving routing problems without the requirement of expert knowledge.

Combinatorial Optimization

Approximation of a Pareto Set Segment Using a Linear Model with Sharing Variables

no code implementations30 Mar 2024 Ping Guo, Qingfu Zhang, Xi Lin

In many real-world applications, the Pareto Set (PS) of a continuous multiobjective optimization problem can be a piecewise continuous manifold.

Multiobjective Optimization

Self-Improved Learning for Scalable Neural Combinatorial Optimization

no code implementations28 Mar 2024 Fu Luo, Xi Lin, Zhenkun Wang, Xialiang Tong, Mingxuan Yuan, Qingfu Zhang

The end-to-end neural combinatorial optimization (NCO) method shows promising performance in solving complex combinatorial optimization problems without the need for expert design.

Combinatorial Optimization

Spikewhisper: Temporal Spike Backdoor Attacks on Federated Neuromorphic Learning over Low-power Devices

no code implementations27 Mar 2024 Hanqing Fu, Gaolei Li, Jun Wu, Jianhua Li, Xi Lin, Kai Zhou, Yuchen Liu

Federated neuromorphic learning (FedNL) leverages event-driven spiking neural networks and federated learning frameworks to effectively execute intelligent analysis tasks over amounts of distributed low-power devices but also perform vulnerability to poisoning attacks.

Federated Learning

What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception

1 code implementation15 Mar 2024 Wanfang Su, Lixing Chen, Yang Bai, Xi Lin, Gaolei Li, Zhe Qu, Pan Zhou

The core philosophy of CMiMC is to preserve discriminative information of individual views in the collaborative view by maximizing mutual information between pre- and post-collaboration features while enhancing the efficacy of collaborative views by minimizing the loss function of downstream tasks.

Contrastive Learning Philosophy

Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume

no code implementations8 Mar 2024 Ping Guo, Cheng Gong, Xi Lin, Zhiyuan Yang, Qingfu Zhang

To address this gap, we propose a new metric termed adversarial hypervolume, assessing the robustness of deep learning models comprehensively over a range of perturbation intensities from a multi-objective optimization standpoint.

Adversarial Robustness Benchmarking +1

Smooth Tchebycheff Scalarization for Multi-Objective Optimization

1 code implementation29 Feb 2024 Xi Lin, Xiaoyuan Zhang, Zhiyuan Yang, Fei Liu, Zhenkun Wang, Qingfu Zhang

Multi-objective optimization problems can be found in many real-world applications, where the objectives often conflict each other and cannot be optimized by a single solution.

valid

Escaping Local Optima in Global Placement

no code implementations28 Feb 2024 Ke Xue, Xi Lin, Yunqi Shi, Shixiong Kai, Siyuan Xu, Chao Qian

Placement is crucial in the physical design, as it greatly affects power, performance, and area metrics.

Multi-Task Learning for Routing Problem with Cross-Problem Zero-Shot Generalization

1 code implementation23 Feb 2024 Fei Liu, Xi Lin, Zhenkun Wang, Qingfu Zhang, Xialiang Tong, Mingxuan Yuan

The results show that the unified model demonstrates superior performance in the eleven VRPs, reducing the average gap to around 5% from over 20% in the existing approach and achieving a significant performance boost on benchmark datasets as well as a real-world logistics application.

Attribute Combinatorial Optimization +2

UMOEA/D: A Multiobjective Evolutionary Algorithm for Uniform Pareto Objectives based on Decomposition

no code implementations14 Feb 2024 Xiaoyuan Zhang, Xi Lin, Yichi Zhang, Yifan Chen, Qingfu Zhang

Multiobjective optimization (MOO) is prevalent in numerous applications, in which a Pareto front (PF) is constructed to display optima under various preferences.

Diversity Multiobjective Optimization

PMGDA: A Preference-based Multiple Gradient Descent Algorithm

no code implementations14 Feb 2024 Xiaoyuan Zhang, Xi Lin, Qingfu Zhang

It is desirable in many multi-objective machine learning applications, such as multi-task learning with conflicting objectives and multi-objective reinforcement learning, to find a Pareto solution that can match a given preference of a decision maker.

Multi-Objective Reinforcement Learning Multi-Task Learning +2

L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks

2 code implementations27 Jan 2024 Ping Guo, Fei Liu, Xi Lin, Qingchuan Zhao, Qingfu Zhang

In the rapidly evolving field of machine learning, adversarial attacks present a significant challenge to model robustness and security.

Adversarial Attack Computational Efficiency +3

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks

no code implementations19 Jan 2024 Ping Guo, Zhiyuan Yang, Xi Lin, Qingchuan Zhao, Qingfu Zhang

Black-box query-based attacks constitute significant threats to Machine Learning as a Service (MLaaS) systems since they can generate adversarial examples without accessing the target model's architecture and parameters.

Adversarial Purification

Dealing with Structure Constraints in Evolutionary Pareto Set Learning

no code implementations31 Oct 2023 Xi Lin, Xiaoyuan Zhang, Zhiyuan Yang, Qingfu Zhang

In this work, we make the first attempt to incorporate the structure constraints into the whole solution set by a single Pareto set model, which can be efficiently learned by a simple evolutionary stochastic optimization method.

Multiobjective Optimization Stochastic Optimization

Large Language Model for Multi-objective Evolutionary Optimization

1 code implementation19 Oct 2023 Fei Liu, Xi Lin, Zhenkun Wang, Shunyu Yao, Xialiang Tong, Mingxuan Yuan, Qingfu Zhang

It is also promising to see the operator only learned from a few instances can have robust generalization performance on unseen problems with quite different patterns and settings.

Evolutionary Algorithms Language Modeling +5

Online Relocating and Matching of Ride-Hailing Services: A Model-Based Modular Approach

no code implementations13 Oct 2023 Chang Gao, Xi Lin, Fang He, Xindi Tang

This study proposes an innovative model-based modular approach (MMA) to dynamically optimize order matching and vehicle relocation in a ride-hailing platform.

Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization

1 code implementation NeurIPS 2023 Fu Luo, Xi Lin, Fei Liu, Qingfu Zhang, Zhenkun Wang

Neural combinatorial optimization (NCO) is a promising learning-based approach for solving challenging combinatorial optimization problems without specialized algorithm design by experts.

Combinatorial Optimization Decoder

Targeting relative risk heterogeneity with causal forests

1 code implementation26 Sep 2023 Vik Shirvaikar, Xi Lin, Chris Holmes

The estimation of heterogeneous treatment effects (HTE) across different subgroups in a population is of significant interest in clinical trial analysis.

Differentially Private Graph Neural Network with Importance-Grained Noise Adaption

no code implementations9 Aug 2023 Yuxin Qi, Xi Lin, Jun Wu

We propose NAP-GNN, a node-importance-grained privacy-preserving GNN algorithm with privacy guarantees based on adaptive differential privacy to safeguard node information.

Graph Learning Graph Neural Network +1

Continuation Path Learning for Homotopy Optimization

1 code implementation24 Jul 2023 Xi Lin, Zhiyuan Yang, Xiaoyuan Zhang, Qingfu Zhang

Homotopy optimization is a traditional method to deal with a complicated optimization problem by solving a sequence of easy-to-hard surrogate subproblems.

Decision Making

Exploring the Cognitive Dynamics of Artificial Intelligence in the Post-COVID-19 and Learning 3.0 Era: A Case Study of ChatGPT

no code implementations3 Feb 2023 Lingfei Luan, Xi Lin, Wenbiao Li

The ultimate objective of this study is to instigate a scholarly discourse on the interplay between technological advancements in education and the evolution of human learning patterns, raising the question of whether technology is driving human evolution or vice versa.

Ethics

Pareto Set Learning for Expensive Multi-Objective Optimization

1 code implementation16 Oct 2022 Xi Lin, Zhiyuan Yang, Xiaoyuan Zhang, Qingfu Zhang

This work represents the first attempt to model the Pareto set for expensive multi-objective optimization.

Bayesian Optimization Decision Making

Pareto Set Learning for Neural Multi-objective Combinatorial Optimization

1 code implementation29 Mar 2022 Xi Lin, Zhiyuan Yang, Qingfu Zhang

In this work, we generalize the idea of neural combinatorial optimization, and develop a learning-based approach to approximate the whole Pareto set for a given MOCO problem without further search procedure.

Combinatorial Optimization Traveling Salesman Problem

Template NeRF: Towards Modeling Dense Shape Correspondences from Category-Specific Object Images

no code implementations8 Nov 2021 Jianfei Guo, Zhiyuan Yang, Xi Lin, Qingfu Zhang

By representing object instances within the same category as shape and appearance variation of a shared NeRF template, our proposed method can achieve dense shape correspondences reasoning on images for a wide range of object classes.

3D-Aware Image Synthesis Keypoint Detection +1

Preference Conditioned Neural Multi-objective Combinatorial Optimization

no code implementations ICLR 2022 Xi Lin, Zhiyuan Yang, Qingfu Zhang

In this work, we generalize the idea of neural combinatorial optimization, and develop a learning-based approach to approximate the whole Pareto set for a given MOCO problem without further search procedure.

Combinatorial Optimization Traveling Salesman Problem

A Data-Driven Sparse Polynomial Chaos Expansion Method to Assess Probabilistic Total Transfer Capability for Power Systems with Renewables

no code implementations27 Oct 2020 Xiaoting Wang, Xiaozhe Wang, Hao Sheng, Xi Lin

The increasing uncertainty level caused by growing renewable energy sources (RES) and aging transmission networks poses a great challenge in the assessment of total transfer capability (TTC) and available transfer capability (ATC).

Computational Efficiency

Superconductor-metal quantum transition at the EuO-KTaO3 interface

no code implementations23 Oct 2020 Yang Ma, Jiasen Niu, Wenyu Xing, Yunyan Yao, Ranran Cai, Jirong Sun, X. C. Xie, Xi Lin, Wei Han

Superconductivity has been one of the most fascinating quantum states of matter for over several decades.

Superconductivity Mesoscale and Nanoscale Physics Materials Science

Controllable Pareto Multi-Task Learning

no code implementations13 Oct 2020 Xi Lin, Zhiyuan Yang, Qingfu Zhang, Sam Kwong

With a fixed model capacity, the tasks would be conflicted with each other, and the system usually has to make a trade-off among learning all of them together.

Multiobjective Optimization Multi-Task Learning

Multi-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning Approach

no code implementations13 Feb 2020 Ke Zhang, Meng Li, Zhengchao Zhang, Xi Lin, Fang He

Multi-vehicle routing problem with soft time windows (MVRPSTW) is an indispensable constituent in urban logistics distribution systems.

Computational Efficiency Decoder +4

Pareto Multi-Task Learning

1 code implementation NeurIPS 2019 Xi Lin, Hui-Ling Zhen, Zhenhua Li, Qingfu Zhang, Sam Kwong

Recently, a novel method is proposed to find one single Pareto optimal solution with good trade-off among different tasks by casting multi-task learning as multiobjective optimization.

Multiobjective Optimization Multi-Task Learning

A Keyframe-based Continuous Visual SLAM for RGB-D Cameras via Nonparametric Joint Geometric and Appearance Representation

1 code implementation2 Dec 2019 Xi Lin, Dingyi Sun, Tzu-Yuan Lin, Ryan M. Eustice, Maani Ghaffari

The experimental evaluations using publicly available RGB-D benchmarks show that the developed keyframe selection technique using continuous visual odometry outperforms its robust dense (and direct) visual odometry equivalent.

Visual Odometry

Nonlinear Collaborative Scheme for Deep Neural Networks

no code implementations4 Nov 2018 Hui-Ling Zhen, Xi Lin, Alan Z. Tang, Zhenhua Li, Qingfu Zhang, Sam Kwong

Different from them, in this paper, we aim to link the generalization ability of a deep network to optimizing a new objective function.

Multistep Speed Prediction on Traffic Networks: A Graph Convolutional Sequence-to-Sequence Learning Approach with Attention Mechanism

no code implementations24 Oct 2018 Zhengchao Zhang, Meng Li, Xi Lin, Yinhai Wang, Fang He

Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.