Search Results for author:
Found 89 papers, 30 papers with code
Automatic Entity State Annotation using the VerbNet Semantic Parser
Tracking entity states is a natural language processing task assumed to require human annotation.
Random Inverse Problems Over Graphs: Decentralized Online Learning
By equivalently transferring the distributed learning problem in RKHS to the random inverse problem over graphs, we propose a decentralized online learning algorithm in RKHS based on non-stationary and non-independent online data streams, and prove that the algorithm is mean square and almost surely strongly consistent if the operators induced by the random input data satisfy the infinite-dimensional spatio-temporal persistence of excitation condition.
Scenario-Agnostic Zero-Trust Defense with Explainable Threshold Policy: A Meta-Learning Approach
The increasing connectivity and intricate remote access environment have made traditional perimeter-based network defense vulnerable.
Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective
Based on self-fitting, we provide new insights into the existing methods to mitigate CO and extend CO to multi-step adversarial training.
Commitment with Signaling under Double-sided Information Asymmetry
This work considers a double-sided information asymmetry in a Bayesian Stackelberg game, where the leader's realized action, sampled from the mixed strategy commitment, is hidden from the follower.
Efficient Generalization Improvement Guided by Random Weight Perturbation
To fully uncover the great potential of deep neural networks (DNNs), various learning algorithms have been developed to improve the model's generalization ability.
On Multi-head Ensemble of Smoothed Classifiers for Certified Robustness
Randomized Smoothing (RS) is a promising technique for certified robustness, and recently in RS the ensemble of multiple deep neural networks (DNNs) has shown state-of-the-art performances.
Multi-Speaker Expressive Speech Synthesis via Multiple Factors Decoupling
This paper aims to synthesize the target speaker's speech with desired speaking style and emotion by transferring the style and emotion from reference speech recorded by other speakers.
Decentralized Policy Gradient for Nash Equilibria Learning of General-sum Stochastic Games
For the case with exact pseudo gradients, we design a two-loop algorithm by the equivalence of Nash equilibrium and variational inequality problems.
On the Resilience of Traffic Networks under Non-Equilibrium Learning
We investigate the resilience of learning-based \textit{Intelligent Navigation Systems} (INS) to informational flow attacks, which exploit the vulnerabilities of IT infrastructure and manipulate traffic condition data.
MUG: Interactive Multimodal Grounding on User Interfaces
To investigate the problem, we create a new dataset that consists of 77, 820 sequences of human user-agent interaction on mobile interfaces in which 20% involves multiple rounds of interactions.
Event-Triggered Extended State Observer Based Distributed Control of Nonlinear Vehicle Platoons
Finally, we give the range of the control parameters to ensure the stability of the vehicle platoon system.
Sampling Attacks on Meta Reinforcement Learning: A Minimax Formulation and Complexity Analysis
It leads to two online attack schemes: Intermittent Attack and Persistent Attack, which enable the attacker to learn an optimal sampling attack, defined by an $\epsilon$-first-order stationary point, within $\mathcal{O}(\epsilon^{-2})$ iterations.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Decentralized Online Regularized Learning Over Random Time-Varying Graphs
We study the decentralized online regularized linear regression algorithm over random time-varying graphs.
Progressive Multi-scale Consistent Network for Multi-class Fundus Lesion Segmentation
The two proposed PFF and DAB blocks can be integrated with the off-the-shelf backbone networks to address the two issues of multi-scale and feature inconsistency in the multi-class segmentation of fundus lesions, which will produce better feature representation in the feature space.
Hilbert Curve Projection Distance for Distribution Comparison
Distribution comparison plays a central role in many machine learning tasks like data classification and generative modeling.
Trainable Weight Averaging for Fast Convergence and Better Generalization
Recently, an interesting attempt is stochastic weight averaging (SWA), which significantly improves the generalization by simply averaging the solutions at the tail stage of training.
MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion
Many Image Quality Assessment(IQA) algorithms have been designed to tackle this problem.
Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Moreover, the explicit prosody features used in the prosody predicting module can increase the diversity of synthetic speech by adjusting the value of prosody features.
M2DGR: A Multi-sensor and Multi-scenario SLAM Dataset for Ground Robots
We introduce M2DGR: a novel large-scale dataset collected by a ground robot with a full sensor-suite including six fish-eye and one sky-pointing RGB cameras, an infrared camera, an event camera, a Visual-Inertial Sensor (VI-sensor), an inertial measurement unit (IMU), a LiDAR, a consumer-grade Global Navigation Satellite System (GNSS) receiver and a GNSS-IMU navigation system with real-time kinematic (RTK) signals.
One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation
One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness.
Subspace Adversarial Training
Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust.
Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks
We implement ESB as an accelerator and quantitatively evaluate its efficiency on FPGAs.
Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion
Specifically, prosodic features are used to explicit model prosody, while VAE and reference encoder are used to implicitly model prosody, which take Mel spectrum and bottleneck feature as input respectively.
The Confluence of Networks, Games and Learning
In addition to existing research works on game-theoretic learning over networks, we highlight several new angles and research endeavors on learning in games that are related to recent developments in artificial intelligence.
DeepBlur: A Simple and Effective Method for Natural Image Obfuscation
There is a growing privacy concern due to the popularity of social media and surveillance systems, along with advances in face recognition software.
Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces
Deep neural networks (DNNs) usually contain massive parameters, but there is redundancy such that it is guessed that the DNNs could be trained in low-dimensional subspaces.
Differentially Private Imaging via Latent Space Manipulation
There is growing concern about image privacy due to the popularity of social media and photo devices, along with increasing use of face recognition systems.
Strongly Connected Topology Model and Confirmation-based Propagation Method for Cross-chain Interaction
Meanwhile, different from legacy networks, the propagation method is required to keep the data validity.
Distributed, Parallel, and Cluster Computing
A Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection
In ophthalmology, early fundus screening is an economic and effective way to prevent blindness caused by ophthalmic diseases.
Signal identification with Kalman Filter towards background-free neutrinoless double beta decay searches in gaseous detectors
Particle tracks and differential energy loss measured in high pressure gaseous detectors can be exploited for event identification in neutrinoless double beta decay~($0\nu \beta \beta$) searches.
Instrumentation and Detectors High Energy Physics - Experiment
Applications of Deep Learning in Fundus Images: A Review
The use of fundus images for the early screening of eye diseases is of great clinical importance.
Blackwell Online Learning for Markov Decision Processes
This work provides a novel interpretation of Markov Decision Processes (MDP) from the online optimization viewpoint.
Slow Control System for PandaX-III experiment
The PandaX-III experiment uses high pressure gaseous time projection chamber to search for the neutrinoless double beta decay of $^{136}$Xe.
Anomaly Detection
High Energy Physics - Experiment
Instrumentation and Detectors
Locally-Aware Constrained Games on Networks
We use \textit{awareness levels} to capture the scope of the network constraints that players are aware of.
An Empirical-cum-Statistical Approach to Power-Performance Characterization of Concurrent GPU Kernels
Growing deployment of power and energy efficient throughput accelerators (GPU) in data centers demands enhancement of power-performance co-optimization capabilities of GPUs.
Distributed, Parallel, and Cluster Computing Hardware Architecture Graphics
Learning Causal Semantic Representation for Out-of-Distribution Prediction
Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output.
Towards Robust Neural Networks via Orthogonal Diversity
Despite of the efficiency in defending specific attacks, adversarial training is benefited from the data augmentation, which does not contribute to the robustness of DNN itself and usually suffers from accuracy drop on clean data as well as inefficiency in unknown attacks.
UnQovering Stereotyping Biases via Underspecified Questions
Our broad study reveals that (1) all these models, with and without fine-tuning, have notable stereotyping biases in these classes; (2) larger models often have higher bias; and (3) the effect of fine-tuning on bias varies strongly with the dataset and the model size.
Learn Robust Features via Orthogonal Multi-Path
To defend adversarial attacks, we design a block containing multiple paths to learn robust features and the parameters of these paths are required to be orthogonal with each other.
On Data Augmentation for Extreme Multi-label Classification
Our contributions are two-factored: (1) we introduce a new state-of-the-art classifier that uses label attention with RoBERTa and combine it with our augmentation framework for further improvement; (2) we present a broad study on how effective are different augmentation methods in the XMC task.
Attention-SLAM: A Visual Monocular SLAM Learning from Human Gaze
This paper proposes a novel simultaneous localization and mapping (SLAM) approach, namely Attention-SLAM, which simulates human navigation mode by combining a visual saliency model (SalNavNet) with traditional monocular visual SLAM.
Distributed Stochastic Optimization With Unbounded Subgradients Over Randomly Time-Varying Networks
Motivated by distributed statistical learning over uncertain communication networks, we study distributed stochastic optimization by networked nodes to cooperatively minimize a sum of convex cost functions.
OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings
Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks.
Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
Extracting effective deep features to represent content and style information is the key to universal style transfer.
Causality and Batch Reinforcement Learning: Complementary Approaches To Planning In Unknown Domains
Reinforcement learning algorithms have had tremendous successes in online learning settings.
VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization
Quantization has been proven to be an effective method for reducing the computing and/or storage cost of DNNs.
AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack
In this paper, we first generalize the formulation of edge-perturbing attacks and strictly prove the vulnerability of GCNs to such attacks in node classification tasks.
Structured Tuning for Semantic Role Labeling
We start with a strong baseline (RoBERTa) to validate the impact of our approach, and show that our framework outperforms the baseline by learning to comply with declarative constraints.
Cooperative Extended State Observer Based Control of Vehicle Platoons With Arbitrarily Small Time Headway
By using the stability theory of perturbed linear systems, we show that the control parameters can be properly designed to ensure the closed-loop and L2 string stabilities for any given positive time headway.
Self-Learning with Rectification Strategy for Human Parsing
For the global error, we first transform category-wise features into a high-level graph model with coarse-grained structural information, and then decouple the high-level graph to reconstruct the category features.
SFE-GACN: A Novel Unknown Attack Detection Method Using Intra Categories Generation in Embedding Space
In this paper, we propose a novel unknown attack detection method based on Intra Categories Generation in Embedding Space, namely SFE-GACN, which might be the solution of few-shot problem.
A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors
The experimental results show that the proposed method can surprisingly converge in a few iterations and achieve an accuracy of 91. 15% on a real IMU dataset, demonstrating the efficiency and effectiveness of the proposed method.
Phylogenetic Study of 2019-nCoV by Using Alignment Free Method (Evolutionary Bifurcation of Novel Coronavirus Mutants)
It is found that there exist three types of virus mutations, namely, the mutation among sub-branches of the same branch, the off-root mutation and the root-oriented mutation between large branches of the tree.
Mutually unbiased measurement based entanglement witnesses
We study entanglement witness and present a construction of entanglement witnesses in terms of the mutually unbiased measurements (MUMs).
Quantum Physics
Component Attention Guided Face Super-Resolution Network: CAGFace
To make the best use of the underlying structure of faces, the collective information through face datasets and the intermediate estimates during the upsampling process, here we introduce a fully convolutional multi-stage neural network for 4$\times$ super-resolution for face images.
A Logic-Driven Framework for Consistency of Neural Models
While neural models show remarkable accuracy on individual predictions, their internal beliefs can be inconsistent across examples.
On Measuring and Mitigating Biased Inferences of Word Embeddings
Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them.
Decentralized Cooperative Online Estimation With Random Observation Matrices, Communication Graphs and Time Delays
Firstly, for the delay-free case, we show that the algorithm gains can be designed properly such that all nodes' estimates converge to the true parameter in mean square and almost surely if the observation matrices and communication graphs satisfy the stochastic spatiotemporal persistence of excitation condition.
On Convergence Rate of Adaptive Multiscale Value Function Approximation For Reinforcement Learning
In this paper, we propose a generic framework for devising an adaptive approximation scheme for value function approximation in reinforcement learning, which introduces multiscale approximation.
A Pvalue-guided Anomaly Detection Approach Combining Multiple Heterogeneous Log Parser Algorithms on IIoT Systems
In this paper, we use blockchain to prevent logs from being tampered with and propose a pvalue-guided anomaly detection approach.
Cryptography and Security
Augmenting Neural Networks with First-order Logic
Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset.
Beauty Learning and Counterfactual Inference
This work showcases a new approach for causal discovery by leveraging user experiments and recent advances in photo-realistic image editing, demonstrating a potential of identifying causal factors and understanding complex systems counterfactually.
T-SVD Based Non-convex Tensor Completion and Robust Principal Component Analysis
Tensor completion and robust principal component analysis have been widely used in machine learning while the key problem relies on the minimization of a tensor rank that is very challenging.
BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving
Instead, BLVD aims to provide a platform for the tasks of dynamic 4D (3D+temporal) tracking, 5D (4D+interactive) interactive event recognition and intention prediction.
Understanding Beauty via Deep Facial Features
The concept of beauty has been debated by philosophers and psychologists for centuries, but most definitions are subjective and metaphysical, and deficit in accuracy, generality, and scalability.
Student's t-Generative Adversarial Networks
We propose a new method referring to conditional GAN, which equipments the latent noise with mixture of Student's t-distribution with attention mechanism in addition to class information.
Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension
Neural networks models have gained unprecedented popularity in natural language processing due to their state-of-the-art performance and the flexible end-to-end training scheme.
Structure Learning of Deep Networks via DNA Computing Algorithm
The indicates that: 1) Using DNA computing algorithm to learn deep architectures is feasible; 2) Local minima should not be a problem of deep networks; 3) We can use early stop to kill the models with the bad performance just after several runs of training.
GPU based Parallel Optimization for Real Time Panoramic Video Stitching
In order to solve these problems, we propose a real-time panoramic video stitching framework. The framework we propose mainly consists of three algorithms, LORB image feature extraction algorithm, feature point matching algorithm based on LSH and GPU parallel video stitching algorithm based on CUDA. The experiment results show that the algorithm mentioned can improve the performance in the stages of feature extraction of images stitching and matching, the running speed of which is 11 times than that of the traditional ORB algorithm and 639 times than that of the traditional SIFT algorithm.
Semi-supervised Text Regression with Conditional Generative Adversarial Networks
Enormous online textual information provides intriguing opportunities for understandings of social and economic semantics.
HashTran-DNN: A Framework for Enhancing Robustness of Deep Neural Networks against Adversarial Malware Samples
Adversarial machine learning in the context of image processing and related applications has received a large amount of attention.
YouTube AV 50K: An Annotated Corpus for Comments in Autonomous Vehicles
With one billion monthly viewers, and millions of users discussing and sharing opinions, comments below YouTube videos are rich sources of data for opinion mining and sentiment analysis.
Aspect Based Sentiment Analysis with Gated Convolutional Networks
Aspect based sentiment analysis (ABSA) can provide more detailed information than general sentiment analysis, because it aims to predict the sentiment polarities of the given aspects or entities in text.
Collaborative Filtering with Topic and Social Latent Factors Incorporating Implicit Feedback
First, we propose a novel model {\em \mbox{MR3}} to jointly model three sources of information (i. e., ratings, item reviews, and social relations) effectively for rating prediction by aligning the latent factors and hidden topics.
BTS-DSN: Deeply Supervised Neural Network with Short Connections for Retinal Vessel Segmentation
Results: The proposed BTS-DSN has been verified on DRIVE, STARE and CHASE_DB1 datasets, and showed competitive performance over other state-of-the-art methods.
A Class-Incremental Learning Method Based on One Class Support Vector Machine
Then the support vectors of the old classes and the support vectors of the new class are reused to train 1VS1 classifiers for the confuse part.
HSI-CNN: A Novel Convolution Neural Network for Hyperspectral Image
In this paper, we propose a novel convolutional neural network framework for the characteristics of hyperspectral image data, called HSI-CNN.
MTNA: A Neural Multi-task Model for Aspect Category Classification and Aspect Term Extraction On Restaurant Reviews
Online reviews are valuable resources not only for consumers to make decisions before purchase, but also for providers to get feedbacks for their services or commodities.
Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms
To address these issues, collaborative filtering (CF), one of the recommendation techniques relying on the interaction data only, as well as the online multi-armed bandit mechanisms, capable of achieving the balance between exploitation and exploration, are adopted in the online interactive recommendation settings, by assuming independent items (i. e., arms).
Structure-measure: A New Way to Evaluate Foreground Maps
Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a SM and a GT map.
Lesion detection and Grading of Diabetic Retinopathy via Two-stages Deep Convolutional Neural Networks
We propose an automatic diabetic retinopathy (DR) analysis algorithm based on two-stages deep convolutional neural networks (DCNN).
Z$_{2}$ spin liquid phase on the kagome lattice: a new saddle point
The Z$_{2}$ state is found to be slightly more stable than the extensively studied U(1) gapless Dirac spin liquid state in both the $J_{2}\neq0$ and the $J_{2}=0$ case and to possess a small spinon gap for $J_{2}<0. 2$.
Strongly Correlated Electrons
Skopus: Mining top-k sequential patterns under leverage
It combines (1) a novel definition of the expected support for a sequential pattern - a concept on which most interestingness measures directly rely - with (2) SkOPUS: a new branch-and-bound algorithm for the exact discovery of top-k sequential patterns under a given measure of interest.
