Search Results for author:
Found 92 papers, 24 papers with code
A Dual Adaptive Assignment Approach for Robust Graph-Based Clustering
Graph clustering is an essential aspect of network analysis that involves grouping nodes into separate clusters.
Beware of Calibration Data for Pruning Large Language Models
As large language models (LLMs) are widely applied across various fields, model compression has become increasingly crucial for reducing costs and improving inference efficiency.
LLM-based Translation Inference with Iterative Bilingual Understanding
The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance.
Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers
Building upon this, we discover through theoretical analysis and numerical experiments that two initialization techniques, partition of unity (PoU) and variance scaling (VS), enhance the effective rank, thereby accelerating the convergence of training error.
CoT-ST: Enhancing LLM-based Speech Translation with Multimodal Chain-of-Thought
We propose CoT-ST, a speech translation model that utilizes multimodal CoT to decompose speech translation into sequential steps of speech recognition and translation.
CLIP-based Camera-Agnostic Feature Learning for Intra-camera Person Re-Identification
To address this, we propose a novel framework called CLIP-based Camera-Agnostic Feature Learning (CCAFL) for ICS ReID.
Differentially Private Multimodal Laplacian Dropout (DP-MLD) for EEG Representative Learning
Recently, multimodal electroencephalogram (EEG) learning has shown great promise in disease detection.
TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models
In this paper, we analyze the core mechanisms of previous predominant adversarial attack methods, revealing that 1) the distributions of importance score differ markedly among victim models, restricting the transferability; 2) the sequential attack processes induces substantial time overheads.
Benchmarking LLMs for Translating Classical Chinese Poetry:Evaluating Adequacy, Fluency, and Elegance
This task requires not only adequacy in translating culturally and historically significant content but also a strict adherence to linguistic fluency and poetic elegance.
EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection
Recently, deep learning has demonstrated promising results in enhancing the accuracy of vulnerability detection and identifying vulnerabilities in software.
Efffcient Sensing Parameter Estimation with Direct Clutter Mitigation in Perceptive Mobile Networks
In this work, we investigate sensing parameter estimation in the presence of clutter in perceptive mobile networks (PMNs) that integrate radar sensing into mobile communications.
A fast neural hybrid Newton solver adapted to implicit methods for nonlinear dynamics
In this work, we propose a novel deep learning based hybrid Newton's method to accelerate this solution of the nonlinear time step system for stiff time-evolution nonlinear equations.
DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms
Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation.
Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
Large language models (LLMs) have showcased impressive multilingual machine translation ability.
Memorization in deep learning: A survey
Deep Learning (DL) powered by Deep Neural Networks (DNNs) has revolutionized various domains, yet understanding the intricacies of DNN decision-making and learning processes remains a significant challenge.
AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs.
Automatic Differentiation is Essential in Training Neural Networks for Solving Differential Equations
Specifically, through comprehensive experimental and theoretical analyses conducted on random feature models and two-layer neural networks, we discover that the defined truncated entropy serves as a reliable metric for quantifying the residual loss of random feature models and the training speed of neural networks for both AD and FD methods.
Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization
To address the challenges of low-rank compression in LLMs, we conduct empirical research on the low-rank characteristics of large models.
Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration
To address this challenge, DeePEn maps the probability distribution of each model from its own probability space to a universal relative space based on the relative representation theory, and performs aggregation.
RL in Markov Games with Independent Function Approximation: Improved Sample Complexity Bound under the Local Access Model
Up to a logarithmic dependence on the size of the state space, Lin-Confident-FTRL learns $\epsilon$-CCE with a provable optimal accuracy bound $O(\epsilon^{-2})$ and gets rids of the linear dependency on the action space, while scaling polynomially with relevant problem parameters (such as the number of agents and time horizon).
Domain Adversarial Active Learning for Domain Generalization Classification
Our results demonstrate that the DAAL algorithm can achieve strong generalization ability with fewer data resources, thereby reducing data annotation costs in domain generalization tasks.
ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization
Our convergence analysis and experiments prove this is a better way to improve convergence stability and rate in ZO-SGD.
ElasticLaneNet: An Efficient Geometry-Flexible Approach for Lane Detection
The task of lane detection involves identifying the boundaries of driving areas in real-time.
A Deep Representation Learning-based Speech Enhancement Method Using Complex Convolution Recurrent Variational Autoencoder
{Compared to our preliminary work, DCCRN-VAE introduces a more sophisticated DCCRN structure and probability distribution for DRL.
Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuning
However, existing ADA methods fail to account for the confounder properly, which is the root cause of the source data distribution that differs from the target domains.
Elastic Interaction Energy-Informed Real-Time Traffic Scene Perception
Urban segmentation and lane detection are two important tasks for traffic scene perception.
Energy stable neural network for gradient flow equations
In this paper, we propose an energy stable network (EStable-Net) for solving gradient flow equations.
Client-side Gradient Inversion Against Federated Learning from Poisoning
For the first time, we show the feasibility of a client-side adversary with limited knowledge being able to recover the training samples from the aggregated global model.
SHAPE: A Sample-adaptive Hierarchical Prediction Network for Medication Recommendation
Effectively medication recommendation with complex multimorbidity conditions is a critical task in healthcare.
Large Transformers are Better EEG Learners
The proposed approach allows for seamless integration of pre-trained vision models and language models in time series decoding tasks, particularly in EEG data analysis.
Model Provenance via Model DNA
Understanding the life cycle of the machine learning (ML) model is an intriguing area of research (e. g., understanding where the model comes from, how it is trained, and how it is used).
Stability Analysis Framework for Particle-based Distance GANs with Wasserstein Gradient Flow
In this paper, we analyze the stability of the training process of these GANs from the perspective of probability density dynamics.
Score-based Transport Modeling for Mean-Field Fokker-Planck Equations
We use the score-based transport modeling method to solve the mean-field Fokker-Planck equations, which we call MSBTM.
Diff-ID: An Explainable Identity Difference Quantification Framework for DeepFake Detection
We then visualize the identity loss between the test and the reference image from the image differences of the aligned pairs, and design a custom metric to quantify the identity loss.
Elastic Interaction Energy-Based Generative Model: Approximation in Feature Space
We adopt the GAN framework and replace the discriminator with a feature transformation network to map the data into a latent space.
DOSnet as a Non-Black-Box PDE Solver: When Deep Learning Meets Operator Splitting
Deep neural networks (DNNs) recently emerged as a promising tool for analyzing and solving complex differential equations arising in science and engineering applications.
An Efficient Split Fine-tuning Framework for Edge and Cloud Collaborative Learning
To enable the pre-trained models to be fine-tuned with local data on edge devices without sharing data with the cloud, we design an efficient split fine-tuning (SFT) framework for edge and cloud collaborative learning.
A Two-Stage Deep Representation Learning-Based Speech Enhancement Method Using Variational Autoencoder and Adversarial Training
To obtain a higher quality enhanced speech, we propose a two-stage DRL-based SE method through adversarial training.
Accelerating Diffusion Models via Pre-segmentation Diffusion Sampling for Medical Image Segmentation
Based on the Denoising Diffusion Probabilistic Model (DDPM), medical image segmentation can be described as a conditional image generation task, which allows to compute pixel-wise uncertainty maps of the segmentation and allows an implicit ensemble of segmentations to boost the segmentation performance.
Multi-modal Dynamic Graph Network: Coupling Structural and Functional Connectome for Disease Diagnosis and Classification
Graph neural networks have been proven to be of great importance in modeling brain connectome networks and relating disease-specific patterns.
Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles
We study the stochastic contextual bandit with knapsacks (CBwK) problem, where each action, taken upon a context, not only leads to a random reward but also costs a random resource consumption in a vector form.
GOLLIC: Learning Global Context beyond Patches for Lossless High-Resolution Image Compression
Besides the latent variable unique to each patch, we introduce shared latent variables between patches to construct the global context.
The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices
However, recent advanced backdoor attacks show that this assumption is no longer valid in dynamic backdoors where the triggers vary from input to input, thereby defeating the existing defenses.
Estimating Brain Age with Global and Local Dependencies
The brain age has been proven to be a phenotype of relevance to cognitive performance and brain disease.
Hiding Your Signals: A Security Analysis of PPG-based Biometric Authentication
It reduces the success rate of rPPG spoofing attacks in user authentication to 0. 05.
Approximation of Functionals by Neural Network without Curse of Dimensionality
In this paper, we establish a neural network to approximate functionals, which are maps from infinite dimensional spaces to finite dimensional spaces.
Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters
We took natural language processing (NLP) as an example to show how Nebula-I works in different training phases that include: a) pre-training a multilingual language model using two remote clusters; and b) fine-tuning a machine translation model using knowledge distilled from pre-trained models, which run through the most popular paradigm of recent deep learning.
A deep representation learning speech enhancement method using $β$-VAE
In previous work, we proposed a variational autoencoder-based (VAE) Bayesian permutation training speech enhancement (SE) method (PVAE) which indicated that the SE performance of the traditional deep neural network-based (DNN) method could be improved by deep representation learning (DRL).
CATNet: Cross-event Attention-based Time-aware Network for Medical Event Prediction
It is a time-aware, event-aware and task-adaptive method with the following advantages: 1) modeling heterogeneous information and temporal information in a unified way and considering temporal irregular characteristics locally and globally respectively, 2) taking full advantage of correlations among different types of events via cross-event attention.
Multimodal data matters: language model pre-training over structured and unstructured electronic health records
As two important textual modalities in electronic health records (EHR), both structured data (clinical codes) and unstructured data (clinical narratives) have recently been increasingly applied to the healthcare domain.
A Bayesian Permutation training deep representation learning method for speech enhancement with variational autoencoder
This means that the proposed method can apply the VAE to model both speech and noise signals, which is totally different from the previous VAE-based SE works.
ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
A unified framework named ERNIE 3. 0 was recently proposed for pre-training large-scale knowledge enhanced models and trained a model with 10 billion parameters.
Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives
Background: Electronic Health Records (EHRs) contain rich information of patients' health history, which usually include both structured and unstructured data.
Simple Recurrent Neural Networks is all we need for clinical events predictions using EHR data
As a result, deep learning models developed for sequence modeling, like recurrent neural networks (RNNs) are common architecture for EHR-based clinical events predictive models.
GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph
Previous works indicate that the glyph of Chinese characters contains rich semantic information and has the potential to enhance the representation of Chinese characters.
Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks
Pruning is a model compression method that removes redundant parameters in deep neural networks (DNNs) while maintaining accuracy.
Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services.
Internal Wasserstein Distance for Adversarial Attack and Defense
Existing attack methods often construct adversarial examples relying on some metrics like the $\ell_p$ distance to perturb samples.
Machine Learning Based Cyber Attacks Targeting on Controlled Information: A Survey
Stealing attack against controlled information, along with the increasing number of information leakage incidents, has become an emerging cyber security threat in recent years.
Continuum Model and Numerical Method for Dislocation Structure and Energy of Grain Boundaries
We present a continuum model to determine the dislocation structure and energy of low angle grain boundaries in three dimensions.
Materials Science
Continuum model for dislocation structures of semicoherent interfaces
In our continuum model, the dislocation structure of a semicoherent interface is obtained by minimizing the energy of the equilibrium dislocation network with respect to all the possible Burgers vectors, subject to the constraint of the Frank-Bilby equation.
Materials Science
DeFuzz: Deep Learning Guided Directed Fuzzing
Fuzzing is one of the most effective technique to identify potential software vulnerabilities.
An Elastic Interaction-Based Loss Function for Medical Image Segmentation
The commonly used loss functions in the deep segmentation task are pixel-wise loss functions.
Analysis of Trending Topics and Text-based Channels of Information Delivery in Cybersecurity
We further compare the identified 16 security categories across different sources based on their popularity and impact.
Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction
Deep learning (DL) based predictive models from electronic health records (EHR) deliver impressive performance in many clinical tasks.
Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text
Chinese word segmentation is necessary to provide word-level information for Chinese named entity recognition (NER) systems.
Chinese Named Entity Recognition
Chinese Word Segmentation
+6
A Study of Data Pre-processing Techniques for Imbalanced Biomedical Data Classification
However, previous studies usually focused on different classifiers, and overlook the class imbalance problem in real-world biomedical datasets.
Man-in-the-Middle Attacks against Machine Learning Classifiers via Malicious Generative Models
First, such attacks must acquire the outputs from the models by multiple times before actually launching attacks, which is difficult for the MitM adversary in practice.
Hybrid Neural Tagging Model for Open Relation Extraction
Furthermore, we propose a hybrid neural network model (HNN4ORT) for open relation tagging.
Naive Bayes and BiLSTM Ensemble for Discriminating between Mainland and Taiwan Variation of Mandarin Chinese
Automatic dialect identification is a more challengingctask than language identification, as it requires the ability to discriminate between varieties of one language.
Daedalus: Breaking Non-Maximum Suppression in Object Detection via Adversarial Examples
Experimental results demonstrate that the attack effectively stops NMS from filtering redundant bounding boxes.
A Truthful FPTAS Mechanism for Emergency Demand Response in Colocation Data Centers
Next, we prove that our mechanism is an FPTAS, i. e., it can be approximated within $1 + \epsilon$ for any given $\epsilon > 0$, while the running time of our mechanism is polynomial in $n$ and $1/\epsilon$, where $n$ is the number of tenants in the datacenter.
Computer Science and Game Theory
ML-Net: multi-label classification of biomedical texts with deep neural networks
Due to this nature, the multi-label text classification task is often considered to be more challenging compared to the binary or multi-class text classification problems.
An objective-adaptive refinement criterion based on modified ridge extraction method for finite-time Lyapunov exponent (FTLE) calculation
High-accuracy and high-efficiency finite-time Lyapunov exponent (FTLE) calculation method has long been a research hot point, and adaptive refinement method is a kind of method in this field.
Fluid Dynamics
Triple Trustworthiness Measurement for Knowledge Graph
The Knowledge graph (KG) uses the triples to describe the facts in the real world.
Chinese User Service Intention Classification Based on Hybrid Neural Network
It is difficult for the intelligent system to understand the semantics of user demand which leads to poor recognition effect, because of the noise in user requirement descriptions.
Android HIV: A Study of Repackaging Malware for Evading Machine-Learning Detection
In contrast to existing works, the adversarial examples crafted by our method can also deceive recent machine learning based detectors that rely on semantic features such as control-flow-graph.
Cryptography and Security
Automated Big Traffic Analytics for Cyber Security
Network traffic analytics technology is a cornerstone for cyber security systems.
Cryptography and Security
Defending against Adversarial Attack towards Deep Neural Networks via Collaborative Multi-task Training
For example, proactive defending methods are invalid against grey-box or white-box attacks, while reactive defending methods are challenged by low-distortion adversarial examples or transferring adversarial examples.
Task-specific Word Identification from Short Texts Using a Convolutional Neural Network
The other case study on fake review detection shows that our approach can identify the fake-review words/phrases.
Wikipedia Vandal Early Detection: from User Behavior to User Embedding
In particular, we develop a multi-source long-short term memory network (M-LSTM) to model user behaviors by using a variety of user edit aspects as inputs, including the history of edit reversion information, edit page titles and categories.
Incorporating Label Dependency for Answer Quality Tagging in Community Question Answering via CNN-LSTM-CRF
In community question answering (cQA), the quality of answers are determined by the matching degree between question-answer pairs and the correlation among the answers.
Representation Learning Models for Entity Search
We focus on the problem of learning distributed representations for entity search queries, named entities, and their short descriptions.
The Dependent Random Measures with Independent Increments in Mixture Models
One of the propositions of the dependent random measures is that the atoms of the posterior distribution are shared amongst groups, and hence groups can borrow information from each other.
Smoothed Hierarchical Dirichlet Process: A Non-Parametric Approach to Constraint Measures
The key novelty of this model is that we place a temporal constraint amongst the nearby discrete measures $\{G_j\}$ in the form of symmetric Kullback-Leibler (KL) Divergence with a fixed bound $B$.
Can Uncertainty Management be Realized in a Finite Totally Ordered Probability Algebra?
In this paper, the feasibility of using finite totally ordered probability models under Alelinnas's Theory of Probabilistic Logic [Aleliunas, 1988] is investigated.
