Search Results for author:
Found 108 papers, 38 papers with code
TSLANet: Rethinking Transformers for Time Series Representation Learning
Time series data, characterized by its intrinsic long and short-range dependencies, poses a unique challenge across analytical applications.
Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning
However, its performance is very dependent on the training data and performs poorly on data outside the training set, which leads to poor noise robustness and Versatility of such methods.
Balancing Fairness and Accuracy in Data-Restricted Binary Classification
Applications that deal with sensitive information may have restrictions placed on the data available to a machine learning (ML) classifier.
K-Link: Knowledge-Link Graph from LLMs for Enhanced Representation Learning in Multivariate Time-Series Data
To capture these dependencies, Graph Neural Networks (GNNs) have emerged as powerful tools, yet their effectiveness is restricted by the quality of graph construction from MTS data.
PowerSkel: A Device-Free Framework Using CSI Signal for Human Skeleton Estimation in Power Station
WiFi-based human pose estimation is a suitable method for monitoring power operations due to its low cost, device-free, and robustness to various illumination conditions. In this paper, a novel Channel State Information (CSI)-based pose estimation framework, namely PowerSkel, is developed to address these challenges.
MMSR: Symbolic Regression is a Multimodal Task
The SR problem is solved as a pure multimodal problem, and contrastive learning is also introduced in the training process for modal alignment to facilitate later modal feature fusion.
Balancing Spectral, Temporal and Spatial Information for EEG-based Alzheimer's Disease Classification
Here, we systematically investigate the importance of spatial information relative to spectral or temporal information by varying the proportion of each dimension for AD classification.
Stochastic Graph Heat Modelling for Diffusion-based Connectivity Retrieval
Here, we combine the graph heat equation with the stochastic heat equation, which ultimately yields a model for multivariate time signals on a graph.
Self-evolving Autoencoder Embedded Q-Network
During the evolution of the autoencoder architecture, a bias-variance regulatory strategy is employed to elicit the optimal response from the RL agent.
Evolving Restricted Boltzmann Machine-Kohonen Network for Online Clustering
A novel online clustering algorithm is presented where an Evolving Restricted Boltzmann Machine (ERBM) is embedded with a Kohonen Network called ERBM-KNet.
Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset.
PruneSymNet: A Symbolic Neural Network and Pruning Algorithm for Symbolic Regression
Therefore, a greedy pruning algorithm is proposed to prune the network into a subnetwork while ensuring the accuracy of data fitting.
Marabou 2.0: A Versatile Formal Analyzer of Neural Networks
This paper serves as a comprehensive system description of version 2. 0 of the Marabou framework for formal analysis of neural networks.
Discovering Mathematical Formulas from Data via GPT-guided Monte Carlo Tree Search
To optimize the trade-off between efficiency and versatility, we introduce SR-GPT, a novel algorithm for symbolic regression that integrates Monte Carlo Tree Search (MCTS) with a Generative Pre-Trained Transformer (GPT).
Explaining Time Series via Contrastive and Locally Sparse Perturbations
Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns.
A Novel Paradigm for Neural Computation: X-Net with Learnable Neurons and Adaptable Structure
1, The type of activation function is single and relatively fixed, which leads to poor "unit representation ability" of the network, and it is often used to solve simple problems with very complex networks; 2, the network structure is not adaptive, it is easy to cause network structure redundant or insufficient.
Towards Efficient Verification of Quantized Neural Networks
Quantization replaces floating point arithmetic with integer arithmetic in deep neural network models, providing more efficient on-device inference with less power and memory.
Understanding Concepts in Graph Signal Processing for Neurophysiological Signal Analysis
The experimental section focuses on the role of graph frequency in data classification, with applications to neuroimaging.
SEA++: Multi-Graph-based High-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation
In this paper, we propose SEnsor Alignment (SEA) for MTS-UDA, aiming to reduce domain discrepancy at both the local and global sensor levels.
MetaSymNet: A Dynamic Symbolic Regression Network Capable of Evolving into Arbitrary Formulations
To address these issues, we propose MetaSymNet, a novel neural network that dynamically adjusts its structure in real-time, allowing for both expansion and contraction.
A Canonical Data Transformation for Achieving Inter- and Within-group Fairness
The mapping is constructed to preserve the relative relationship between the scores obtained from the unprocessed feature vectors of individuals from the same demographic group, guaranteeing within-group fairness.
Graph Convolutional Network with Connectivity Uncertainty for EEG-based Emotion Recognition
To address these challenges, this study introduces the distribution-based uncertainty method to represent spatial dependencies and temporal-spectral relativeness in EEG signals based on Graph Convolutional Network (GCN) architecture that adaptively assigns weights to functional aggregate node features, enabling effective long-path capturing while mitigating over-smoothing phenomena.
Graph Neural Network-based EEG Classification: A Survey
Graph neural networks (GNN) are increasingly used to classify EEG for tasks such as emotion recognition, motor imagery and neurological diseases and disorders.
A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data
Instead of searching for expressions within a large search space, we explore DySymNet with various structures and optimize them to identify expressions that better-fitting the data.
Information Forensics and Security: A quarter-century-long journey
Information Forensics and Security (IFS) is an active R&D area whose goal is to ensure that people use devices, data, and intellectual properties for authorized purposes and to facilitate the gathering of solid evidence to hold perpetrators accountable.
Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data
For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances, enabling us to fully model the ST dependencies by considering the correlations between DEDT.
Graph-Aware Contrasting for Multivariate Time-Series Classification
As MTS data typically originate from multiple sensors, ensuring spatial consistency becomes essential for the overall performance of contrastive learning on MTS data.
Interdisciplinary Fairness in Imbalanced Research Proposal Topic Inference: A Hierarchical Transformer-based Method with Selective Interpolation
The objective of topic inference in research proposals aims to obtain the most suitable disciplinary division from the discipline system defined by a funding agency.
Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks
On ImageNet, we achieve up to 4. 7% and 4. 6% higher top-1 accuracy compared to other methods for VGG-16 and ResNet-50, respectively.
Unlimited Knowledge Distillation for Action Recognition in the Dark
To address this issue, we propose an unlimited knowledge distillation (UKD) in this paper.
Source-Free Domain Adaptation with Temporal Imputation for Time Series Data
The existing SFDA methods that are mainly designed for visual applications may fail to handle the temporal dynamics in time series, leading to impaired adaptation performance.
AutoHint: Automatic Prompt Optimization with Hint Generation
This paper presents AutoHint, a novel framework for automatic prompt engineering and optimization for Large Language Models (LLM).
Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data
More specifically, a feature-domain discriminator is employed to align teacher's and student's representations for universal knowledge transfer.
Revisiting Computer-Aided Tuberculosis Diagnosis
This dataset enables the training of sophisticated detectors for high-quality CTD.
Traceable Group-Wise Self-Optimizing Feature Transformation Learning: A Dual Optimization Perspective
Feature transformation aims to reconstruct an effective representation space by mathematically refining the existing features.
A Cascaded Approach for ultraly High Performance Lesion Detection and False Positive Removal in Liver CT Scans
In this work, we customize a multi-object labeling tool for multi-phase CT images, which is used to curate a large-scale dataset containing 1, 631 patients with four-phase CT images, multi-organ masks, and multi-lesion (six major types of liver lesions confirmed by pathology) masks.
Incorporating Prior Knowledge in Deep Learning Models via Pathway Activity Autoencoders
Through comprehensive comparisons among various learning models, we show that, despite having access to a smaller set of features, our PAAE and PAVAE models achieve better out-of-set reconstruction results compared to common methodologies.
Adaptive Gated Graph Convolutional Network for Explainable Diagnosis of Alzheimer's Disease using EEG Data
Graph neural network (GNN) models are increasingly being used for the classification of electroencephalography (EEG) data.
ECG-CL: A Comprehensive Electrocardiogram Interpretation Method Based on Continual Learning
From the perspective of intelligent wearable applications, the possibility of a comprehensive ECG interpretation algorithm based on single-lead ECGs is also confirmed.
Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation
We thus consider a more realistic \textit{Few-Shot Video-based Domain Adaptation} (FSVDA) scenario where we adapt video models with only a few target video samples.
CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting
Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome.
MetaGrad: Adaptive Gradient Quantization with Hypernetworks
A popular track of network compression approach is Quantization aware Training (QAT), which accelerates the forward pass during the neural network training and inference.
Convex Bounds on the Softmax Function with Applications to Robustness Verification
The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well.
Beyond Discrete Selection: Continuous Embedding Space Optimization for Generative Feature Selection
Furthermore, we reconstruct feature selection solutions using these embeddings and select the feature subset with the highest performance for downstream tasks as the optimal subset.
Label-efficient Time Series Representation Learning: A Review
The scarcity of labeled data is one of the main challenges of applying deep learning models on time series data in the real world.
Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with GraphST
Lastly, compared to other methods, GraphST’s cell type deconvolution achieved higher accuracy on simulated data and better captured spatial niches such as the germinal centers of the lymph node in experimentally acquired data.
RWSC-Fusion: Region-Wise Style-Controlled Fusion Network for the Prohibited X-Ray Security Image Synthesis
Automatic prohibited item detection in security inspection X-ray images is necessary for transportation. The abundance and diversity of the X-ray security images with prohibited item, termed as prohibited X-ray security images, are essential for training the detection model.
Traceable Automatic Feature Transformation via Cascading Actor-Critic Agents
Feature transformation for AI is an essential task to boost the effectiveness and interpretability of machine learning (ML).
On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approach
To address the non-identifiability of PNS, we resort to a lower bound of PNS that can be optimized via counterfactual estimation, and propose a framework of Necessary and Sufficient Explanation for GNN (NSEG) via optimizing that lower bound.
Contrastive Domain Adaptation for Time-Series via Temporal Mixup
Specifically, we propose a novel temporal mixup strategy to generate two intermediate augmented views for the source and target domains.
Self-supervised Learning for Label-Efficient Sleep Stage Classification: A Comprehensive Evaluation
The past few years have witnessed a remarkable advance in deep learning for EEG-based sleep stage classification (SSC).
Hierarchical MixUp Multi-label Classification with Imbalanced Interdisciplinary Research Proposals
In response to this question, we propose a hierarchical mixup multiple-label classification framework, which we called H-MixUp.
Self-Optimizing Feature Transformation
Feature transformation aims to extract a good representation (feature) space by mathematically transforming existing features.
SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance
Remarkably, under our latency requirement of 1900us on CPU, SwiftPruner achieves a 0. 86% higher AUC than the state-of-the-art uniform sparse baseline for BERT-Mini on a large scale real-world dataset.
Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification
Specifically, we propose time-series specific weak and strong augmentations and use their views to learn robust temporal relations in the proposed temporal contrasting module, besides learning discriminative representations by our proposed contextual contrasting module.
Leveraging Endo- and Exo-Temporal Regularization for Black-box Video Domain Adaptation
To enable video models to be applied seamlessly across video tasks in different environments, various Video Unsupervised Domain Adaptation (VUDA) methods have been proposed to improve the robustness and transferability of video models.
A Generalized Probabilistic Monitoring Model with Both Random and Sequential Data
Many multivariate statistical analysis methods and their corresponding probabilistic counterparts have been adopted to develop process monitoring models in recent decades.
Multi-Omic Data Integration and Feature Selection for Survival-based Patient Stratification via Supervised Concrete Autoencoders
We also perform a feature selection stability analysis on our models and notice that there is a power-law relationship with features which are commonly associated with survival.
Bispectrum-based Cross-frequency Functional Connectivity: Classification of Alzheimer's disease
Cross-bispectrum, a higher-order spectral analysis, is used to measure the nonlinear FC and is compared with the cross-spectrum, which only measures the linear FC within bands.
A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges
We believe that this technical review can help to promote a sustainable development of AI R&D activities for the research community.
Real-time Speech Emotion Recognition Based on Syllable-Level Feature Extraction
A set of syllable-level formant features is extracted and fed into a single hidden layer neural network that makes predictions for each syllable as opposed to the conventional approach of using a sophisticated deep learner to make sentence-wide predictions.
RadioSES: mmWave-Based Audioradio Speech Enhancement and Separation System
Speech enhancement and separation have been a long-standing problem, especially with the recent advances using a single microphone.
WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma
According to the technical reports of the top-tier teams, CAM is still the most popular approach in WSSS.
Data Augmentation
Weakly supervised Semantic Segmentation
+1
Learning Local and Global Temporal Contexts for Video Semantic Segmentation
Specifically, we uniformly sample certain frames from the video and extract global contextual prototypes by k-means.
Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction
Chemical reaction prediction, involving forward synthesis and retrosynthesis prediction, is a fundamental problem in organic synthesis.
ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data
Our evaluation includes adapting state-of-the-art visual domain adaptation methods to time series data as well as the recent methods specifically developed for time series data.
Separable-HoverNet and Instance-YOLO for Colon Nuclei Identification and Counting
Nuclear segmentation, classification and quantification within Haematoxylin & Eosin stained histology images enables the extraction of interpretable cell-based features that can be used in downstream explainable models in computational pathology (CPath).
Lumbar Bone Mineral Density Estimation from Chest X-ray Images: Anatomy-aware Attentive Multi-ROI Modeling
Osteoporosis is a common chronic metabolic bone disease often under-diagnosed and under-treated due to the limited access to bone mineral density (BMD) examinations, e. g. via Dual-energy X-ray Absorptiometry (DXA).
Motif Graph Neural Network
However, standard GNNs in the neighborhood aggregation paradigm suffer from limited discriminative power in distinguishing \emph{high-order} graph structures as opposed to \emph{low-order} structures.
Self-supervised Autoregressive Domain Adaptation for Time Series Data
Second, we propose a novel autoregressive domain adaptation technique that incorporates temporal dependency of both source and target features during domain alignment.
A Systematic Evaluation of Domain Adaptation Algorithms On Time Series Data
Our evaluation includes adaptations of state-of-the-art visual domain adaptation methods to time series data in addition to recent methods specifically developed for time series data.
Multi-Source Video Domain Adaptation with Temporal Attentive Moment Alignment
Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in real-world scenarios.
A Multi-Channel Ratio-of-Ratios Method for Noncontact Hand Video Based SpO2 Monitoring Using Smartphone Cameras
Experimental results show that our proposed blood oxygen estimation method can reach a mean absolute error of 1. 26% when a pulse oximeter is used as a reference, outperforming the traditional RoR method by 25%.
Remote Blood Oxygen Estimation From Videos Using Neural Networks
Blood oxygen saturation (SpO$_2$) is an essential indicator of respiratory functionality and is receiving increasing attention during the COVID-19 pandemic.
ADAST: Attentive Cross-domain EEG-based Sleep Staging Framework with Iterative Self-Training
Second, we design an iterative self-training strategy to improve the classification performance on the target domain via target domain pseudo labels.
Time-Series Representation Learning via Temporal and Contextual Contrasting
In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC), to learn time-series representation from unlabeled data.
Ranked #1 on
Recognizing And Localizing Human Actions
on HAR
Automatic Sleep Stage Classification
Contrastive Learning
+9
Feasibility Study on Intra-Grid Location Estimation Using Power ENF Signals
In this study, we demonstrate that it is possible to pinpoint the location-of-recording to a certain geographical resolution using power signal recordings containing strong ENF traces.
An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG
The MRCNN can extract low and high frequency features and the AFR is able to improve the quality of the extracted features by modeling the inter-dependencies between the features.
Ranked #1 on
Automatic Sleep Stage Classification
on Sleep-EDF
Opportunistic Screening of Osteoporosis Using Plain Film Chest X-ray
In this paper, we propose a method to predict BMD from Chest X-ray (CXR), one of the most common, accessible, and low-cost medical image examinations.
Characterising Alzheimer's Disease with EEG-based Energy Landscape Analysis
Energy landscape analysis is a method that can be used to quantify these dynamics.
FFConv: Fast Factorized Convolutional Neural Network Inference on Encrypted Data
Despite the faster HECNN inference, the mainstream packing schemes Dense Packing (DensePack) and Convolution Packing (ConvPack) introduce expensive rotation overhead, which prolongs the inference latency of HECNN for deeper and wider CNN architectures.
Cross-domain Joint Dictionary Learning for ECG Inference from PPG
The inverse problem of inferring electrocardiogram (ECG) from photoplethysmogram (PPG) is an emerging research direction that combines the easy measurability of PPG and the rich clinical knowledge of ECG for long-term continuous cardiac monitoring.
Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-constrained Optimization
This paper proposes a robust and accurate method that effectively exploits the anatomical knowledge of the spine to facilitate vertebra localization and identification.
Inferring ECG from PPG for Continuous Cardiac Monitoring Using Lightweight Neural Network
It is also infeasible to expect persistently active user participation for long-term continuous cardiac monitoring in order to capture these and other types of abnormalities of the heart.
Assessing Robustness of Text Classification through Maximal Safe Radius Computation
Neural network NLP models are vulnerable to small modifications of the input that maintain the original meaning but result in a different prediction.
Attention Sequence to Sequence Model for Machine Remaining Useful Life Prediction
Accurate estimation of remaining useful life (RUL) of industrial equipment can enable advanced maintenance schedules, increase equipment availability and reduce operational costs.
Recent Advances in Network-based Methods for Disease Gene Prediction
Thirdly, an empirical analysis is conducted to evaluate the performance of the selected methods across seven diseases.
Transparency Tools for Fairness in AI (Luskin)
The three tools are: - A new definition of fairness called "controlled fairness" with respect to choices of protected features and filters.
Towards Threshold Invariant Fair Classification
This paper introduces the notion of threshold invariant fairness, which enforces equitable performances across different groups independent of the decision threshold.
Multi-View Collaborative Network Embedding
Real-world networks often exist with multiple views, where each view describes one type of interaction among a common set of nodes.
Adaptive Multi-Trace Carving for Robust Frequency Tracking in Forensic Applications
In the field of information forensics, many emerging problems involve a critical step that estimates and tracks weak frequency components in noisy signals.
Contextualized Graph Attention Network for Recommendation with Item Knowledge Graph
Graph neural networks (GNN) have recently been applied to exploit knowledge graph (KG) for recommendation.
Respiratory Rate Estimation from Face Videos
Commercial cameras are promising contact-free sensors, and remote photoplethysmography (rPPG) have been studied to remotely monitor heart rate from face videos.
Robustness Guarantees for Deep Neural Networks on Videos
The widespread adoption of deep learning models places demands on their robustness.
A Deep Framework for Bone Age Assessment based on Finger Joint Localization
In this study, we applied powerful deep neural network and explored a process in the forecast of skeletal bone age with the specifically combine joints images to increase the performance accuracy compared with the whole hand images.
MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation
Unlike most existing approaches which employ a generator to deal with domain difference, MMEN focuses on learning the categorical information from unlabeled target samples with the help of labeled source samples.
A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level performance on several long-standing tasks.
SL$^2$MF: Predicting Synthetic Lethality in Human Cancers via Logistic Matrix Factorization
Moreover, we also incorporate biological knowledge about genes from protein-protein interaction (PPI) data and Gene Ontology (GO).
A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees
In this paper, we study two variants of pointwise robustness, the maximum safe radius problem, which for a given input sample computes the minimum distance to an adversarial example, and the feature robustness problem, which aims to quantify the robustness of individual features to adversarial perturbations.
Concolic Testing for Deep Neural Networks
Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program.
Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the $L_0$ Norm
In this paper we focus on the $L_0$ norm and aim to compute, for a trained DNN and an input, the maximal radius of a safe norm ball around the input within which there are no adversarial examples.
Adaptive Cost-sensitive Online Classification
Cost-Sensitive Online Classification has drawn extensive attention in recent years, where the main approach is to directly online optimize two well-known cost-sensitive metrics: (i) weighted sum of sensitivity and specificity; (ii) weighted misclassification cost.
Safety Verification of Deep Neural Networks
Our method works directly with the network code and, in contrast to existing methods, can guarantee that adversarial examples, if they exist, are found for the given region and family of manipulations.
Efficient Estimation of Compressible State-Space Models with Application to Calcium Signal Deconvolution
In this paper, we consider linear state-space models with compressible innovations and convergent transition matrices in order to model spatiotemporally sparse transient events.
Sampling Requirements for Stable Autoregressive Estimation
Assuming that the parameters are compressible, we analyze the performance of the $\ell_1$-regularized least squares as well as a greedy estimator of the parameters and characterize the sampling trade-offs required for stable recovery in the non-asymptotic regime.
Robust Estimation of Self-Exciting Generalized Linear Models with Application to Neuronal Modeling
We consider the problem of estimating self-exciting generalized linear models from limited binary observations, where the history of the process serves as the covariate.
Multi-label ensemble based on variable pairwise constraint projection
For the boosting-like strategy, we employ both the variable pairwise constraints and the bootstrap steps to diversify the base classifiers.
Sparse Norm Filtering
Optimization-based filtering smoothes an image by minimizing a fidelity function and simultaneously preserves edges by exploiting a sparse norm penalty over gradients.
