Search Results for author:
Found 58 papers, 27 papers with code
Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification
However such way might not fully explore the knowledge in PTMs as it is constrained by the difficulty of the task.
Federated Learning via Variational Bayesian Inference: Personalization, Sparsity and Clustering
data, we propose a clustered Bayesian FL model named cFedbayes by learning different prior distributions for different clients.
Robust one-shot estimation over shared networks in the presence of denial-of-service attacks
We consider the following scenario: multiple pairs of agents communicating strategically over shared communication networks in the presence of a jammer who may launch a denial-of-service.
Online Decomposition of Surface Electromyogram into Individual Motor Unit Activities Using Progressive FastICA Peel-off
For decomposing experimental SEMG data, the proposed online method was able to extract an average of 12. 00 +- 3. 46 MUs per trial, with a matching rate of 90. 38% compared with results from the expert-guided offline decomposition.
Surveillance Face Anti-spoofing
In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks.
Efficient Visual Computing with Camera RAW Snapshots
Conventional cameras capture image irradiance on a sensor and convert it to RGB images using an image signal processor (ISP).
Avoiding spurious correlations via logit correction
Empirical studies suggest that machine learning models trained with empirical risk minimization (ERM) often rely on attributes that may be spuriously correlated with the class labels.
An Empirical Study of Automatic Post-Editing
In view of the importance of data augmentation in APE, we separately study the impact of the construction method of artificial corpora and artificial data domain on the performance of APE models.
CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose
Motivated by the progress of visual-language research, we propose that pre-trained language models (e. g., CLIP) can facilitate animal pose estimation by providing rich prior knowledge for describing animal keypoints in text.
Personalized Federated Learning via Variational Bayesian Inference
Federated learning faces huge challenges from model overfitting due to the lack of data and statistical diversity among clients.
Personalized Prompt for Sequential Recommendation
Specifically, we build the personalized soft prefix prompt via a prompt generator based on user profiles and enable a sufficient training of prompts via a prompt-oriented contrastive learning with both prompt- and behavior-based augmentations.
Selective Fairness in Recommendation via Prompts
In this work, we define the selective fairness task, where users can flexibly choose which sensitive attributes should the recommendation model be bias-free.
Experimental quantum adversarial learning with programmable superconducting qubits
Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios and demonstrate an effective defense strategy against adversarial attacks, which provide a valuable guide for quantum artificial intelligence applications with both near-term and future quantum devices.
Robust remote estimation over the collision channel in the presence of an intelligent jammer
We consider a sensor-receiver pair communicating over a wireless channel in the presence of a jammer who may launch a denial-of-service attack.
Multi-view Multi-behavior Contrastive Learning in Recommendation
We argue that MBR models should: (1) model the coarse-grained commonalities between different behaviors of a user, (2) consider both individual sequence view and global graph view in multi-behavior modeling, and (3) capture the fine-grained differences between multiple behaviors of a user.
A two-step backward compatible fullband speech enhancement system
Speech enhancement methods based on deep learning have surpassed traditional methods.
SMDT: Selective Memory-Augmented Neural Document Translation
Existing document-level neural machine translation (NMT) models have sufficiently explored different context settings to provide guidance for target generation.
Large-Scale Video Panoptic Segmentation in the Wild: A Benchmark
In contrast, our large-scale VIdeo Panoptic Segmentation in the Wild (VIPSeg) dataset provides 3, 536 videos and 84, 750 frames with pixel-level panoptic annotations, covering a wide range of real-world scenarios and categories.
Topological and Algebraic Structures of Atanassov's Intuitionistic Fuzzy-Values Space
By introducing a new operator for IFVs via the linear order based on a score function and an accuracy function, we show that such an operator is a strong negation on IFVs.
V2iFi: in-Vehicle Vital Sign Monitoring via Compact RF Sensing
Given the significant amount of time people spend in vehicles, health issues under driving condition have become a major concern.
Personalized Transfer of User Preferences for Cross-domain Recommendation
Specifically, a meta network fed with users' characteristic embeddings is learned to generate personalized bridge functions to achieve personalized transfer of preferences for each user.
A Causal U-net based Neural Beamforming Network for Real-Time Multi-Channel Speech Enhancement
In this work, a new causal U-net based multiple-in-multiple-out structure is proposed for real-time multi-channel speech enhancement.
Sparse Personalized Federated Learning
By incorporating an approximated L1-norm and the correlation between client models and global model into standard FL loss function, the performance on statistical diversity data is improved and the communicational and computational loads required in the network are reduced compared with non-sparse FL.
Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising
Besides, MetaHeac has been successfully deployed in WeChat for the promotion of both contents and advertisements, leading to great improvement in the quality of marketing.
Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users
With the advantage of meta learning which has good generalization ability to novel tasks, we propose a transfer-meta framework for CDR (TMCDR) which has a transfer stage and a meta stage.
Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks
The cold item ID embedding has two main problems: (1) A gap is existing between the cold ID embedding and the deep model.
Optimal exit decision of venture capital under time-inconsistent preferences
Based on venture capitalists' understanding of future preferences, we consider four types of venture capitalists, namely time-consistent venture capitalists, venture capitalists who only realize critical time point inconsistency, naive venture capitalists and sophisticated venture capitalists, of which the latter three are time-inconsistent.
Enhancement of Superconductivity Linked with Linear-in-Temperature/Field Resistivity in Ion-Gated FeSe Films
Iron selenide (FeSe) - the structurally simplest iron-based superconductor, has attracted tremendous interest in the past years.
Superconductivity
Understanding WeChat User Preferences and "Wow" Diffusion
"Top Stories" is a novel friend-enhanced recommendation engine in WeChat, in which users can read articles based on preferences of both their own and their friends.
Graph Representation Learning
Social and Information Networks
UPRec: User-Aware Pre-training for Recommender Systems
Existing sequential recommendation methods rely on large amounts of training data and usually suffer from the data sparsity problem.
FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation
Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world scenarios.
Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction
The current methods for the link prediction taskhavetwonaturalproblems:1)the relation distributions in KGs are usually unbalanced, and 2) there are many unseen relations that occur in practical situations.
Intra-Correlation Encoding for Chinese Sentence Intention Matching
Sentence intention matching is vital for natural language understanding.
Learning to Build User-tag Profile in Recommendation System (UTPM)
User profiling is one of the most important components in recommendation systems, where a user is profiled using demographic (e. g. gender, age, and location) and user behavior information (e. g. browsing and search history).
MLBF-Net: A Multi-Lead-Branch Fusion Network for Multi-Class Arrhythmia Classification Using 12-Lead ECG
MLBF-Net is composed of three components: 1) multiple lead-specific branches for learning the diversity of multi-lead ECG; 2) cross-lead features fusion by concatenating the output feature maps of all branches for learning the integrity of multi-lead ECG; 3) multi-loss co-optimization for all the individual branches and the concatenated network.
Deep Learning Guided Building Reconstruction from Satellite Imagery-derived Point Clouds
For points that belong to the same roof shape, a multi-cue, hierarchical RANSAC approach is proposed for efficient and reliable segmenting and reconstructing the building point cloud.
Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation
In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence.
Unifying Specialist Image Embedding into Universal Image Embedding
Therefore, we propose to distill the knowledge in multiple specialists into a universal embedding to solve this problem.
Detecting and Simulating Artifacts in GAN Fake Images
By using the simulated images to train a spectrum based classifier, even without seeing the fake images produced by the targeted GAN model during training, our approach achieves state-of-the-art performances on detecting fake images generated by popular GAN models such as CycleGAN.
Real-time Attention Based Look-alike Model for Recommender System
Recently, deep learning models play more and more important roles in contents recommender systems.
Super Interaction Neural Network
Recent studies have demonstrated that the convolutional networks heavily rely on the quality and quantity of generated features.
Label Mapping Neural Networks with Response Consolidation for Class Incremental Learning
In this paper, it is the first time to discuss the difficulty without support of old classes in class incremental learning, which is called as softmax suppression problem.
Unsupervised Embedding Learning via Invariant and Spreading Instance Feature
This paper studies the unsupervised embedding learning problem, which requires an effective similarity measurement between samples in low-dimensional embedding space.
Exact Controllability for a Refined Stochastic Wave Equation
By means of a new global Carleman estimate, we establish the exact controllability of our stochastic wave equation with three controls.
Optimization and Control 93B05, 60H15, 93B07, 35B45
FARSA: Fully Automated Roadway Safety Assessment
An emerging approach for conducting such assessments in the United States is through the US Road Assessment Program (usRAP), which rates roads from highest risk (1 star) to lowest (5 stars).
Assessment of central serous chorioretinopathy (CSC) depicted on color fundus photographs using deep Learning
To investigate whether and to what extent central serous chorioretinopathy (CSC) depicted on color fundus photographs can be assessed using deep learning technology.
Optimal Feedback for Stochastic Linear Quadratic Control and Backward Stochastic Riccati Equations in Infinite Dimensions
It is a longstanding unsolved problem to characterize the optimal feedbacks for general SLQs (i. e., stochastic linear quadratic control problems) with random coefficients in infinite dimensions; while the same problem but in finite dimensions was just addressed in a recent work [36].
Optimization and Control Probability 60H15, 93E20, 60H25, 49J30
Second Order Optimality Conditions for Optimal Control Problems of Stochastic Evolution Equations
In this paper, we establish some second order necessary/sufficient optimality conditions for optimal control problems of stochastic evolution equations in infinite dimensions.
Optimization and Control Primary 93E20, Secondary, 60H07, 60H15
SCMA based resource management of D2D communications for maximum sum-revenue
This problem is NP-hard, so we propose a heuristic algorithm based on semi-definite relaxation (SDR) programming to solve it.
Signal Processing
Heated-Up Softmax Embedding
Metric learning aims at learning a distance which is consistent with the semantic meaning of the samples.
Tropical Principal Component Analysis and its Application to Phylogenetics
Principal component analysis is a widely-used method for the dimensionality reduction of a given data set in a high-dimensional Euclidean space.
Combinatorics Populations and Evolution
Learning Spread-out Local Feature Descriptors
We propose a simple, yet powerful regularization technique that can be used to significantly improve both the pairwise and triplet losses in learning local feature descriptors.
Learning Discriminative and Transformation Covariant Local Feature Detectors
Specifically, we extend the covariant constraint proposed by Lenc and Vedaldi by defining the concepts of "standard patch" and "canonical feature" and leverage these to train a novel robust covariant detector.
Learning discriminative and transformation covariant local feature detectors.
Specifically, we extend the covariant constraint proposed by Lenc and Vedaldi [8] by defining the concepts of “standard patch” and “canonical feature” and leverage these to train a novel robust covariant detector.
Spatio-temporal Aware Non-negative Component Representation for Action Recognition
This paper presents a novel mid-level representation for action recognition, named spatio-temporal aware non-negative component representation (STANNCR).
Fast Orthogonal Projection Based on Kronecker Product
We propose a family of structured matrices to speed up orthogonal projections for high-dimensional data commonly seen in computer vision applications.
Deep Transfer Network: Unsupervised Domain Adaptation
In this paper, we propose a new domain adaptation framework named Deep Transfer Network (DTN), where the highly flexible deep neural networks are used to implement such a distribution matching process.
Efficient classification using parallel and scalable compressed model and Its application on intrusion detection
In order to achieve high efficiency of classification in intrusion detection, a compressed model is proposed in this paper which combines horizontal compression with vertical compression.
