Search Results for author:
Found 65 papers, 9 papers with code
Sociolectal Analysis of Pretrained Language Models
Using data from English cloze tests, in which subjects also self-reported their gender, age, education, and race, we examine performance differences of pretrained language models across demographic groups, defined by these (protected) attributes.
Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning
To our knowledge, this paper is the first work that achieves both $\mathcal{O}(\epsilon^{-2})$ sample complexity and $\mathcal{O}(\epsilon^{-2})$ communication complexity in decentralized policy evaluation for cooperative MARL.
Amortized Prompt: Lightweight Fine-Tuning for CLIP in Domain Generalization
For the latter, we propose AP (Amortized Prompt), as a novel approach for domain inference in the form of prompt generation.
CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning
Labels are costly and sometimes unreliable.
Ranked #1 on
Image Classification
on mini WebVision 1.0
Finding the Winning Ticket of BERT for Binary Text Classification via Adaptive Layer Truncation before Fine-tuning
In light of the success of transferring language models into NLP tasks, we ask whether the full BERT model is always the best and does it exist a simple but effective method to find the winning ticket in state-of-the-art deep neural networks without complex calculations.
The channel-spatial attention-based vision transformer network for automated, accurate prediction of crop nitrogen status from UAV imagery
We propose a novel deep learning framework: a channel-spatial attention-based vision transformer (CSVT) for estimating crop N status from large images collected from a UAV in a wheat field.
CXR-Net: An Encoder-Decoder-Encoder Multitask Deep Neural Network for Explainable and Accurate Diagnosis of COVID-19 pneumonia with Chest X-ray Images
The proposed method can provide more detailed high resolution visual explanation for the classification decision, compared to current state-of-the-art visual explanation methods and has a great potential to be used in clinical practice for COVID-19 pneumonia diagnosis.
Cellular Network Radio Propagation Modeling with Deep Convolutional Neural Networks
Deterministic models, such as ray tracing based on physical laws of wave propagation, are more accurate and site specific.
Anarchic Federated Learning
This diverse set of workers necessitates the development of FL algorithms that allow: (1) flexible worker participation that grants the workers' capability to engage in training at will, (2) varying number of local updates (based on computational resources) at each worker along with asynchronous communication with the server, and (3) heterogeneous data across workers.
Towards interpreting computer vision based on transformation invariant optimization
Interpreting how does deep neural networks (DNNs) make predictions is a vital field in artificial intelligence, which hinders wide applications of DNNs.
Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition
Crowdsourcing is regarded as one prospective solution for effective supervised learning, aiming to build large-scale annotated training data by crowd workers.
Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation
Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor using the intermediate data distributions generated for the two domains, which includes an image-to-image translator and a shared-weighted segmentation network.
GT-STORM: Taming Sample, Communication, and Memory Complexities in Decentralized Non-Convex Learning
Decentralized nonconvex optimization has received increasing attention in recent years in machine learning due to its advantages in system robustness, data privacy, and implementation simplicity.
Constructing long-short stock portfolio with a new listwise learn-to-rank algorithm
Our loss function, motivated by the long-short strategy, is endogenously shift-invariant and can be viewed as a direct generalization of ListMLE.
Genetic Algorithm based hyper-parameters optimization for transfer Convolutional Neural Network
Decision of transfer layers and trainable layers is a major task for design of the transfer convolutional neural networks (CNN).
Constraints on interacting dark energy models from time-delay cosmography with seven lensed quasars
When the TD data is added to the CMB+BAO+SN+$H_0$ data, we find that: (i) the coupling parameter $\beta$ in all the considered IDE models is positive within 1$\sigma$ range, implying a mild preference for the case of cold dark matter decaying into dark energy; (ii) all the considered IDE models aggravate the $\sigma_8$ tension, while the $S_8$ tension could be slightly relieved in the IDE model with $Q = \beta H_{0} \rho_{\rm c}$; (iii) the Akaike information criteria of the IDE models with $Q \propto \rho_{\rm c}$ are lower than that of the $\Lambda$CDM model, indicating that these IDE models are more preferred by the current mainstream data.
Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Phenomenology
Phantom Bethe roots in the integrable open spin $1/2$ $XXZ$ chain
Bethe eigenstates are described by two complementary sets of Bethe Ansatz equations for regular roots, one for each invariant subspace.
Statistical Mechanics Mathematical Physics Mathematical Physics Quantum Physics
Phantom Bethe excitations and spin helix eigenstates in integrable periodic and open spin chains
The phantom Bethe roots lead to degeneracies between different magnetization sectors in the periodic case and to the appearance of spin helix states (SHS), i. e. periodically modulated states of chiral nature in both open and closed systems.
Statistical Mechanics Mathematical Physics Mathematical Physics Quantum Physics
Relieving the $H_0$ tension with a new interacting dark energy model
Here we explain this model as a scenario of vacuum energy interacting with matter and radiation.
Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Phenomenology
Designing 24-hour Electrical Power Generator: Thermoradiative Device for Harvesting Energy from Sun and Outer Space
Energy harvesting from sun and outer space using thermoradiative devices (TRD), despite being promising renewable energy sources, are limited only to daytime and nighttime period, respectively.
Applied Physics Mesoscale and Nanoscale Physics
Spectroscopic and Photometric Redshift Estimation by Neural Networks For the China Space Station Optical Survey (CSS-OS)
This indicates that the neural network method is feasible and powerful for spec-z and photo-z estimations in future cosmological surveys.
Photometric Redshift Estimation
Cosmology and Nongalactic Astrophysics
Super strong paramagnetism of aromatic peptides adsorbed with monovalent cations
We experimentally demonstrated that the AYFFF self-assemblies adsorbed with various monovalent cations (Na+, K+, and Li+) show unexpectedly super strong paramagnetism.
Biological Physics
$k$-core in percolated dense graph sequences
Keeping an edge $(i, j)$ of $G_n$ with probability $\min \{ {a^n_{i, j}}/{n}, 1 \}$ independently, we obtain a sequence of random graphs $G_n(\frac{1}{n})$.
Probability Combinatorics
f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning
This naturally gives rise to the following question: Given a set of expert demonstrations, which divergence can recover the expert policy more accurately with higher data efficiency?
A Novel Semi-Supervised Data-Driven Method for Chiller Fault Diagnosis with Unlabeled Data
Usually, the number of labeled data is limited and most data available are unlabeled.
Prediction against a limited adversary
We study the problem of prediction with expert advice with adversarial corruption where the adversary can at most corrupt one expert.
$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning
This naturally gives rise to the following question: Given a set of expert demonstrations, which divergence can recover the expert policy more accurately with higher data efficiency?
Worst-Case-Aware Curriculum Learning for Zero and Few Shot Transfer
Multi-task transfer learning based on pre-trained language encoders achieves state-of-the-art performance across a range of tasks.
An Explainable 3D Residual Self-Attention Deep Neural Network FOR Joint Atrophy Localization and Alzheimer's Disease Diagnosis using Structural MRI
Different from the existing approaches, the novelty of our approach is three-fold: 1) A Residual Self-Attention Deep Neural Network has been proposed to capture local, global and spatial information of MR images to improve diagnostic performance; 2) An explanation method using Gradient-based Localization Class Activation mapping (Grad-CAM) has been introduced to improve the explainable of the proposed method; 3) This work has provided a full end-to-end learning solution for automated disease diagnosis.
A Computer Vision Based Beamforming Scheme for Millimeter Wave Communication in LOS Scenarios
A novel location-aware beamforming scheme for millimeter wave communication is proposed for line of sight (LOS) and low mobility scenarios, in which computer vision is introduced to derive the required position or spatial angular information from the image or video captured by camera(s) co-located with mmWave antenna array at base stations.
A study of the effect of the illumination model on the generation of synthetic training datasets
Our results show that the effect of the illumination model is important, comparable in significance to the network architecture.
A Computer Vision Aided Beamforming Scheme with EM Exposure Control in Outdoor LOS Scenarios
The proposed exposure avoidance method is validated in simulations, and the results show that the finer beam management granularity can guarantee communication quality while reducing the electromagnetic exposure.
Generalization Study of Quantum Neural Network
In this model, we mapped the feature data to a quantum state in Hilbert space firstly, and then implement unitary evolution on it, in the end, we can get the classification result by im-plement measurement on the quantum state.
HF-UNet: Learning Hierarchically Inter-Task Relevance in Multi-Task U-Net for Accurate Prostate Segmentation
In this paper, we tackle the challenging task of prostate segmentation in CT images by a two-stage network with 1) the first stage to fast localize, and 2) the second stage to accurately segment the prostate.
Malicious Experts versus the multiplicative weights algorithm in online prediction
We assume that one of the experts is honest and makes correct prediction with probability $\mu$ at each round.
Complexity of tree-coloring interval graphs equitably
An equitable tree-$k$-coloring of a graph is a vertex $k$-coloring such that each color class induces a forest and the size of any two color classes differ by at most one.
Combinatorics Discrete Mathematics
Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approach
In this paper, we consider the problem of jointly improving data privacy and communication efficiency of distributed edge learning, both of which are critical performance metrics in wireless edge network computing.
ResNetX: a more disordered and deeper network architecture
Our architecture is a natural extension to ResNet, and can be integrated with existing state-of-the-art methods with little effort.
Finite-Time 4-Expert Prediction Problem
We explicitly solve the nonlinear PDE that is the continuous limit of dynamic programming of \emph{expert prediction problem} in finite horizon setting with $N=4$ experts.
Blockchain for Future Smart Grid: A Comprehensive Survey
In this paper, we aim to provide a comprehensive survey on application of blockchain in smart grid.
Cryptography and Security Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Social and Information Networks Systems and Control Systems and Control
Air-Writing Translater: A Novel Unsupervised Domain Adaptation Method for Inertia-Trajectory Translation of In-air Handwriting
As a new way of human-computer interaction, inertial sensor based in-air handwriting can provide a natural and unconstrained interaction to express more complex and richer information in 3D space.
ASYNCHRONOUS MULTI-AGENT GENERATIVE ADVERSARIAL IMITATION LEARNING
Imitation learning aims to inversely learn a policy from expert demonstrations, which has been extensively studied in the literature for both single-agent setting with Markov decision process (MDP) model, and multi-agent setting with Markov game (MG) model.
PolSAR Image Classification Based on Dilated Convolution and Pixel-Refining Parallel Mapping network in the Complex Domain
For general supervised deep learning classification algorithms, the pixel-by-pixel algorithm achieves precise yet inefficient classification with a small number of labeled pixels, whereas the pixel mapping algorithm achieves efficient yet edge-rough classification with more prior labels required.
Byzantine-Resilient Stochastic Gradient Descent for Distributed Learning: A Lipschitz-Inspired Coordinate-wise Median Approach
In this work, we consider the resilience of distributed algorithms based on stochastic gradient descent (SGD) in distributed learning with potentially Byzantine attackers, who could send arbitrary information to the parameter server to disrupt the training process.
Neural Machine Reading Comprehension: Methods and Trends
Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques over the past few years.
Machine Reading Comprehension: a Literature Review
Machine reading comprehension aims to teach machines to understand a text like a human and is a new challenging direction in Artificial Intelligence.
Distributed Linear Model Clustering over Networks: A Tree-Based Fused-Lasso ADMM Approach
In this work, we consider to improve the model estimation efficiency by aggregating the neighbors' information as well as identify the subgroup membership for each node in the network.
Watermark retrieval from 3D printed objects via synthetic data training
We conclude that in our application domain of information retrieval from 3D printed objects, where access to the exact CAD files of the printed objects can be assumed, one can use inexpensive synthetic data to enhance neural network training, reducing the need for the labour intensive process of creating large amounts of hand labelled real data or the need to generate photorealistic synthetic data.
Spatial CUSUM for Signal Region Detection
We develop theoretical properties of the method which indicates that asymptotically SCUSUM can reach high classification accuracy.
The Random Conditional Distribution for Higher-Order Probabilistic Inference
The need to condition distributional properties such as expectation, variance, and entropy arises in algorithmic fairness, model simplification, robustness and many other areas.
On-line Search History-assisted Restart Strategy for Covariance Matrix Adaptation Evolution Strategy
The entire on-line search history of cNrGA is stored in a binary space partitioning (BSP) tree, which is effective for performing local search.
Probabilistic Verification of Fairness Properties via Concentration
As machine learning systems are increasingly used to make real world legal and financial decisions, it is of paramount importance that we develop algorithms to verify that these systems do not discriminate against minorities.
Watermark Retrieval from 3D Printed Objects via Convolutional Neural Networks
We present a method for reading digital data embedded in planar 3D printed surfaces.
Skeleton-based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module
In this paper, we first leverage a robust feature descriptor, path signature (PS), and propose three PS features to explicitly represent the spatial and temporal motion characteristics, i. e., spatial PS (S_PS), temporal PS (T_PS) and temporal spatial PS (T_S_PS).
Ranked #1 on
Gesture Recognition
on ChaLearn 2013
Taming Convergence for Asynchronous Stochastic Gradient Descent with Unbounded Delay in Non-Convex Learning
Understanding the convergence performance of asynchronous stochastic gradient descent method (Async-SGD) has received increasing attention in recent years due to their foundational role in machine learning.
Land use mapping in the Three Gorges Reservoir Area based on semantic segmentation deep learning method
In this paper, we first test the state of the art semantic segmentation deep learning classifiers for LUCC mapping with 7 categories in the TGRA area with rapideye 5m resolution data.
Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections
We argue that such a correction is a useful way to provide feedback to a user when the network's output is different from a desired output.
Sleep Stage Classification Based on Multi-level Feature Learning and Recurrent Neural Networks via Wearable Device
The feature learning framework is designed to extract low- and mid-level features.
FuRongWang at SemEval-2017 Task 3: Deep Neural Networks for Selecting Relevant Answers in Community Question Answering
We describes deep neural networks frameworks in this paper to address the community question answering (cQA) ranking task (SemEval-2017 task 3).
Learning Multi-level Features For Sensor-based Human Action Recognition
This paper proposes a multi-level feature learning framework for human action recognition using a single body-worn inertial sensor.
Blocking Collapsed Gibbs Sampler for Latent Dirichlet Allocation Models
In this article, we introduce a blocking scheme to the collapsed Gibbs sampler for the LDA model which can, with a theoretical guarantee, improve chain mixing efficiency.
End to End Learning for Self-Driving Cars
The system automatically learns internal representations of the necessary processing steps such as detecting useful road features with only the human steering angle as the training signal.
Fingertip in the Eye: A cascaded CNN pipeline for the real-time fingertip detection in egocentric videos
We introduce a new pipeline for hand localization and fingertip detection.
Dynamic Structure Embedded Online Multiple-Output Regression for Stream Data
MORES can \emph{dynamically} learn the structure of the coefficients change in each update step to facilitate the model's continuous refinement.
Max-Margin based Discriminative Feature Learning
In this paper, we propose a new max-margin based discriminative feature learning method.