Search Results for author: Qiang Fu

Found 67 papers, 16 papers with code

On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filtering

1 code implementation6 Jun 2023 Jiayan Guo, Lun Du, Xu Chen, Xiaojun Ma, Qiang Fu, Shi Han, Dongmei Zhang, Yan Zhang

Graph CF has attracted more and more attention in recent years due to its effectiveness in leveraging high-order information in the user-item bipartite graph for better recommendations.

Collaborative Filtering Recommendation Systems

Image Quality Is Not All You Want: Task-Driven Lens Design for Image Classification

no code implementations26 May 2023 Xinge Yang, Qiang Fu, Yunfeng Nie, Wolfgang Heidrich

Experimental results demonstrate the designed image classification lens (``TaskLens'') exhibits higher accuracy compared to conventional imaging-driven lenses, even with fewer lens elements.

Image Classification

Future-conditioned Unsupervised Pretraining for Decision Transformer

1 code implementation26 May 2023 Zhihui Xie, Zichuan Lin, Deheng Ye, Qiang Fu, Wei Yang, Shuai Li

While promising, return conditioning is limited to training data labeled with rewards and therefore faces challenges in learning from unsupervised data.

Decision Making Reinforcement Learning (RL)

Skill-Based Few-Shot Selection for In-Context Learning

no code implementations23 May 2023 Shengnan An, Bo Zhou, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Weizhu Chen, Jian-Guang Lou

Few-shot selection -- selecting appropriate examples for each test instance separately -- is important for in-context learning.

Semantic Parsing

How Do In-Context Examples Affect Compositional Generalization?

no code implementations8 May 2023 Shengnan An, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Jian-Guang Lou, Dongmei Zhang

Compositional generalization--understanding unseen combinations of seen primitives--is an essential reasoning capability in human intelligence.

Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective

no code implementations23 Apr 2023 Yiming Gao, Feiyu Liu, Liang Wang, Zhenjie Lian, Weixuan Wang, Siqin Li, Xianliang Wang, Xianhan Zeng, Rundong Wang, Jiawei Wang, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

MOBA games, e. g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far.

Aberration-Aware Depth-from-Focus

no code implementations8 Mar 2023 Xinge Yang, Qiang Fu, Mohammed Elhoseiny, Wolfgang Heidrich

Computer vision methods for depth estimation usually use simple camera models with idealized optics.

Depth Estimation

Does Deep Learning Learn to Abstract? A Systematic Probing Framework

1 code implementation23 Feb 2023 Shengnan An, Zeqi Lin, Bei Chen, Qiang Fu, Nanning Zheng, Jian-Guang Lou

Abstraction is a desirable capability for deep learning models, which means to induce abstract concepts from concrete instances and flexibly apply them beyond the learning context.

Robust Mid-Pass Filtering Graph Convolutional Networks

1 code implementation16 Feb 2023 Jincheng Huang, Lun Du, Xu Chen, Qiang Fu, Shi Han, Dongmei Zhang

Theoretical analyses guarantee the robustness of signals through the mid-pass filter, and we also shed light on the properties of different frequency signals under adversarial attacks.

Adversarial Attack Node Classification

Homophily-oriented Heterogeneous Graph Rewiring

no code implementations13 Feb 2023 Jiayan Guo, Lun Du, Wendong Bi, Qiang Fu, Xiaojun Ma, Xu Chen, Shi Han, Dongmei Zhang, Yan Zhang

To this end, we propose HDHGR, a homophily-oriented deep heterogeneous graph rewiring approach that modifies the HG structure to increase the performance of HGNN.

Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization

1 code implementation5 Feb 2023 Zichuan Lin, Xiapeng Wu, Mingfei Sun, Deheng Ye, Qiang Fu, Wei Yang, Wei Liu

Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse.

Curriculum Learning for ab initio Deep Learned Refractive Optics

no code implementations2 Feb 2023 Xinge Yang, Qiang Fu, Wolfgang Heidrich

Deep lens optimization has recently emerged as a new paradigm for designing computational imaging systems, however it has been limited to either simple optical systems consisting of a single DOE or metalens, or the fine-tuning of compound lenses from good initial designs.

Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning

no code implementations20 Jan 2023 Haoxuan Pan, Deheng Ye, Xiaoming Duan, Qiang Fu, Wei Yang, Jianping He, Mingfei Sun

We show that, despite such state distribution shift, the policy gradient estimation bias can be reduced in the following three ways: 1) a small learning rate; 2) an adaptive-learning-rate-based optimizer; and 3) KL regularization.

Continuous Control reinforcement-learning +1

RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning

1 code implementation4 Dec 2022 Boxuan Zhao, Jun Zhang, Deheng Ye, Jian Cao, Xiao Han, Qiang Fu, Wei Yang

Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification.

Benchmarking Decision Making +4

DGI: Easy and Efficient Inference for GNNs

no code implementations28 Nov 2022 Peiqi Yin, Xiao Yan, Jinjing Zhou, Qiang Fu, Zhenkun Cai, James Cheng, Bo Tang, Minjie Wang

In this paper, we develop Deep Graph Inference (DGI) -- a system for easy and efficient GNN model inference, which automatically translates the training code of a GNN model for layer-wise execution.

DIGMN: Dynamic Intent Guided Meta Network for Differentiated User Engagement Forecasting in Online Professional Social Platforms

no code implementations22 Oct 2022 Feifan Li, Lun Du, Qiang Fu, Shi Han, Yushu Du, Guangming Lu, Zi Li

Furthermore, based on the dynamic user intent representations, we propose a meta predictor to perform differentiated user engagement forecasting.

Revisiting Discrete Soft Actor-Critic

1 code implementation21 Sep 2022 Haibin Zhou, Zichuan Lin, Junyou Li, Deheng Ye, Qiang Fu, Wei Yang

We study the adaption of soft actor-critic (SAC) from continuous action space to discrete action space.

Atari Games Q-Learning

Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization

no code implementations1 Sep 2022 Tiantian Zhang, Zichuan Lin, Yuxing Wang, Deheng Ye, Qiang Fu, Wei Yang, Xueqian Wang, Bin Liang, Bo Yuan, Xiu Li

A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information.

Bayesian Inference Knowledge Distillation +3

Learning Rate Perturbation: A Generic Plugin of Learning Rate Schedule towards Flatter Local Minima

no code implementations25 Aug 2022 Hengyu Liu, Qiang Fu, Lun Du, Tiancheng Zhang, Ge Yu, Shi Han, Dongmei Zhang

Learning rate is one of the most important hyper-parameters that has a significant influence on neural network training.

MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution

1 code implementation15 Aug 2022 Wendong Bi, Lun Du, Qiang Fu, Yanlin Wang, Shi Han, Dongmei Zhang

Graph Neural Networks (GNNs) have shown expressive performance on graph representation learning by aggregating information from neighbors.

Graph Representation Learning

Sparse Optical Flow-Based Line Feature Tracking

no code implementations7 Apr 2022 Qiang Fu, Hongshan Yu, Islam Ali, Hong Zhang

To achieve this goal, an efficient two endpoint tracking (TET) method is presented: first, describe a given line feature with its two endpoints; next, track the two endpoints based on SOF to obtain two new tracked endpoints by minimizing a pixel-level grayscale residual function; finally, connect the two tracked endpoints to generate a new line feature.

Optical Flow Estimation Pose Estimation

Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models

no code implementations7 Mar 2022 Shengnan An, Yifei Li, Zeqi Lin, Qian Liu, Bei Chen, Qiang Fu, Weizhu Chen, Nanning Zheng, Jian-Guang Lou

This motivates us to propose input-tuning, which fine-tunes both the continuous prompts and the input representations, leading to a more effective way to adapt unfamiliar inputs to frozen PLMs.

Language Modelling Natural Language Understanding +1

HTGN-BTW: Heterogeneous Temporal Graph Network with Bi-Time-Window Training Strategy for Temporal Link Prediction

no code implementations25 Feb 2022 Chongjian Yue, Lun Du, Qiang Fu, Wendong Bi, Hengyu Liu, Yu Gu, Di Yao

The Temporal Link Prediction task of WSDM Cup 2022 expects a single model that can work well on two kinds of temporal graphs simultaneously, which have quite different characteristics and data properties, to predict whether a link of a given type will occur between two given nodes within a given time span.

Link Prediction

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

no code implementations17 Feb 2022 Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas, Nicholay Topin, Zichuan Lin, Junyou Li, Jianing Shi, Deheng Ye, Qiang Fu, Wei Yang, Weijun Hong, Zhongyue Huang, Haicheng Chen, Guangjun Zeng, Yue Lin, Vincent Micheli, Eloi Alonso, François Fleuret, Alexander Nikulin, Yury Belousov, Oleg Svidchenko, Aleksei Shpilman

With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers.

Reasoning Like Program Executors

1 code implementation27 Jan 2022 Xinyu Pi, Qian Liu, Bei Chen, Morteza Ziyadi, Zeqi Lin, Qiang Fu, Yan Gao, Jian-Guang Lou, Weizhu Chen

Reasoning over natural language is a long-standing goal for the research community.

Ranked #2 on Question Answering on DROP Test (using extra training data)

Logical Reasoning Question Answering

JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning

no code implementations7 Dec 2021 Zichuan Lin, Junyou Li, Jianing Shi, Deheng Ye, Qiang Fu, Wei Yang

To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration.

Efficient Exploration Hierarchical Reinforcement Learning +4

Snapshot HDR Video Construction Using Coded Mask

no code implementations5 Dec 2021 Masheal Alghamdi, Qiang Fu, Ali Thabet, Wolfgang Heidrich

This paper study the reconstruction of High Dynamic Range (HDR) video from snapshot-coded LDR video.

Demosaicking Denoising +1

Source Free Unsupervised Graph Domain Adaptation

no code implementations2 Dec 2021 Haitao Mao, Lun Du, Yujia Zheng, Qiang Fu, Zelin Li, Xu Chen, Shi Han, Dongmei Zhang

They utilize labels from the source domain as the supervision signal and are jointly trained on both the source graph and the target graph.

Domain Adaptation Node Classification

Neuron with Steady Response Leads to Better Generalization

no code implementations30 Nov 2021 Qiang Fu, Lun Du, Haitao Mao, Xu Chen, Wei Fang, Shi Han, Dongmei Zhang

Based on the analysis results, we articulate the Neuron Steadiness Hypothesis: the neuron with similar responses to instances of the same class leads to better generalization.

Inductive Bias

GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily

1 code implementation29 Oct 2021 Lun Du, Xiaozhou Shi, Qiang Fu, Xiaojun Ma, Hengyu Liu, Shi Han, Dongmei Zhang

For node-level tasks, GNNs have strong power to model the homophily property of graphs (i. e., connected nodes are more similar) while their ability to capture the heterophily property is often doubtful.

Graph Attention

Learning Diverse Policies in MOBA Games via Macro-Goals

no code implementations NeurIPS 2021 Yiming Gao, Bei Shi, Xueying Du, Liang Wang, Guangwei Chen, Zhenjie Lian, Fuhao Qiu, Guoan Han, Weixuan Wang, Deheng Ye, Qiang Fu, Wei Yang, Lanxiao Huang

Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings.

Dota 2

Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game

no code implementations ICLR 2022 Haobo Fu, Weiming Liu, Shuang Wu, Yijia Wang, Tao Yang, Kai Li, Junliang Xing, Bin Li, Bo Ma, Qiang Fu, Yang Wei

The deep policy gradient method has demonstrated promising results in many large-scale games, where the agent learns purely from its own experience.

Policy Gradient Methods

Diffractive lensless imaging with optimized Voronoi-Fresnel phase

no code implementations28 Sep 2021 Qiang Fu, Dong-Ming Yan, Wolfgang Heidrich

Here we report a diffractive lensless camera with spatially-coded Voronoi-Fresnel phase to achieve superior image quality.

Neural Étendue Expander for Ultra-Wide-Angle High-Fidelity Holographic Display

no code implementations16 Sep 2021 Ethan Tseng, Seung-Hwan Baek, Grace Kuo, Nathan Matsuda, Andrew Maimone, PRANEETH CHAKRAVARTHULA, Qiang Fu, Wolfgang Heidrich, Douglas Lanman, Felix Heide

Holographic displays can generate light fields by dynamically modulating the wavefront of a coherent beam of light using a spatial light modulator, promising rich virtual and augmented reality applications.

Vocal Bursts Intensity Prediction

Neuron Campaign for Initialization Guided by Information Bottleneck Theory

1 code implementation14 Aug 2021 Haitao Mao, Xu Chen, Qiang Fu, Lun Du, Shi Han, Dongmei Zhang

Initialization plays a critical role in the training of deep neural networks (DNN).

A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging

no code implementations30 Jun 2021 Jingang Zhang, Runmu Su, Wenqi Ren, Qiang Fu, Felix Heide, Yunfeng Nie

We present a thorough investigation of these state-of-the-art spectral reconstruction methods from the widespread RGB images.

Spectral Reconstruction

Active-set algorithms based statistical inference for shape-restricted generalized additive Cox regression models

no code implementations29 Jun 2021 Geng Deng, Guangning Xu, Qiang Fu, Xindong Wang, Jing Qin

In this paper, we introduce the shape-restricted inference to the celebrated Cox regression model (SR-Cox), in which the covariate response is modeled as shape-restricted additive functions.


Boosting Offline Reinforcement Learning with Residual Generative Modeling

no code implementations19 Jun 2021 Hua Wei, Deheng Ye, Zhao Liu, Hao Wu, Bo Yuan, Qiang Fu, Wei Yang, Zhenhui Li

While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.

Offline RL Q-Learning +2

Cooperative Multi-Agent Reinforcement Learning with Sequential Credit Assignment

1 code implementation NeurIPS 2021 Yifan Zang, Jinmin He, Kai Li, Lily Cao, Haobo Fu, Qiang Fu, Junliang Xing

In this paper, we propose a cooperative MARL method with sequential credit assignment (SeCA) that deduces each agent's contribution to the team's success one by one to learn better cooperation.

Multi-agent Reinforcement Learning reinforcement-learning +3

MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks

1 code implementation13 May 2021 Menghui Zhu, Minghuan Liu, Jian Shen, Zhicheng Zhang, Sheng Chen, Weinan Zhang, Deheng Ye, Yong Yu, Qiang Fu, Wei Yang

In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem.

Deep Learning based 3D Segmentation: A Survey

no code implementations9 Mar 2021 Yong He, Hongshan Yu, Xiaoyan Liu, Zhengeng Yang, Wei Sun, Yaonan Wang, Qiang Fu, Yanmei Zou, Ajmal Mian

3D object segmentation is a fundamental and challenging problem in computer vision with applications in autonomous driving, robotics, augmented reality and medical image analysis.

Autonomous Driving Semantic Segmentation

Multi-Agent Deep Reinforcement Learning for Request Dispatching in Distributed-Controller Software-Defined Networking

no code implementations6 Feb 2021 Victoria Huang, Gang Chen, Qiang Fu

Recently, distributed controller architectures have been quickly gaining popularity in Software-Defined Networking (SDN).

Reinforcement Learning (RL)

Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search

no code implementations18 Dec 2020 Sheng Chen, Menghui Zhu, Deheng Ye, Weinan Zhang, Qiang Fu, Wei Yang

Hero drafting is essential in MOBA game playing as it builds the team of each side and directly affects the match outcome.

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

no code implementations25 Nov 2020 Deheng Ye, Guibin Chen, Peilin Zhao, Fuhao Qiu, Bo Yuan, Wen Zhang, Sheng Chen, Mingfei Sun, Xiaoqian Li, Siqin Li, Jing Liang, Zhenjie Lian, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang

Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner.

Towards Playing Full MOBA Games with Deep Reinforcement Learning

no code implementations NeurIPS 2020 Deheng Ye, Guibin Chen, Wen Zhang, Sheng Chen, Bo Yuan, Bo Liu, Jia Chen, Zhao Liu, Fuhao Qiu, Hongsheng Yu, Yinyuting Yin, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i. e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes.

Dota 2 reinforcement-learning +1

PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features

1 code implementation16 Sep 2020 Qiang Fu, Jialong Wang, Hongshan Yu, Islam Ali, Feng Guo, Yijia He, Hong Zhang

This paper presents PL-VINS, a real-time optimization-based monocular VINS method with point and line features, developed based on the state-of-the-art point-based VINS-Mono \cite{vins}.

Pose Estimation

Fast ORB-SLAM without Keypoint Descriptors

no code implementations22 Aug 2020 Qiang Fu, Hongshan Yu, Xiaolong Wang, Zhengeng Yang, Hong Zhang, Ajmal Mian

ORB-SLAM2 \cite{orbslam2} is a benchmark method in this domain, however, it consumes significant time for computing descriptors that never get reused unless a frame is selected as a keyframe.

Robotics Computational Geometry I.4.0; I.4.9

Real time backbone for semantic segmentation

no code implementations16 Mar 2019 Zhengeng Yang, Hongshan Yu, Qiang Fu, Wei Sun, Wenyan Jia, Mingui Sun, Zhi-Hong Mao

The rapid development of autonomous driving in recent years presents lots of challenges for scene understanding.

Autonomous Driving Model Compression +2

Optimizing Controller Placement for Software-Defined Networks

no code implementations14 Feb 2019 Victoria Huang, Gang Chen, Qiang Fu, Elliott Wen

In comparison to communication delay, existing literature on the CPP assumes that the influence of controller workload distribution on network performance is negligible.

Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System

no code implementations29 Jan 2019 Muhammad Ammad-Ud-Din, Elena Ivannikova, Suleiman A. Khan, Were Oyomno, Qiang Fu, Kuan Eeik Tan, Adrian Flanagan

In the Federated Learning paradigm, a master machine learning model is distributed to user clients, the clients use their locally stored data and model for both inference and calculating model updates.

BIG-bench Machine Learning Collaborative Filtering +2

Hierarchical Macro Strategy Model for MOBA Game AI

no code implementations19 Dec 2018 Bin Wu, Qiang Fu, Jing Liang, Peng Qu, Xiaoqian Li, Liang Wang, Wei Liu, Wei Yang, Yongsheng Liu

In this paper, we propose a novel learning-based Hierarchical Macro Strategy model for mastering MOBA games, a sub-genre of RTS games.

Catadioptric HyperSpectral Light Field Imaging

no code implementations ICCV 2017 Yujia Xue, Kang Zhu, Qiang Fu, Xilin Chen, Jingyi Yu

In this paper, we present a single camera hyperspectral light field imaging solution that we call Snapshot Plenoptic Imager (SPI).

Noise Robust IOA/CAS Speech Separation and Recognition System For The Third 'CHIME' Challenge

no code implementations21 Sep 2015 Xiaofei Wang, Chao Wu, Pengyuan Zhang, Ziteng Wang, Yong liu, Xu Li, Qiang Fu, Yonghong Yan

This paper presents the contribution to the third 'CHiME' speech separation and recognition challenge including both front-end signal processing and back-end speech recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Calibration of Multiple Fish-Eye Cameras Using a Wand

no code implementations4 Jul 2014 Qiang Fu, Quan Quan, Kai-Yuan Cai

Fish-eye cameras are becoming increasingly popular in computer vision, but their use for 3D measurement is limited partly due to the lack of an accurate, efficient and user-friendly calibration procedure.

Camera Auto-Calibration Camera Calibration

Bethe-ADMM for Tree Decomposition based Parallel MAP Inference

no code implementations26 Sep 2013 Qiang Fu, Huahua Wang, Arindam Banerjee

We present a parallel MAP inference algorithm called Bethe-ADMM based on two ideas: tree-decomposition of the graph and the alternating direction method of multipliers (ADMM).

Tree Decomposition

Fast Marginalized Block Sparse Bayesian Learning Algorithm

no code implementations21 Nov 2012 Benyuan Liu, Zhilin Zhang, Hongqi Fan, Qiang Fu

One typical correlation structure is the intra-block correlation in block sparse signals.


The Annealing Sparse Bayesian Learning Algorithm

no code implementations5 Sep 2012 Benyuan Liu, Hongqi Fan, Zaiqi Lu, Qiang Fu

The performance such as NMSE and F-measure can be greatly improved due to the annealing technique.


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