U-Net-Guided Detection and Measurement of Growth Bands in Atlantic Surfclam Shell Images
Uses U-Net-guided image analysis to detect and measure growth bands in Atlantic surfclam shells, supporting the quantitative analysis of shell imagery.
Publications
Conference and journal publications, organized by year.
Showing all 97 publications
Filter by topic
Filter by type
2026
Augmentation with Reinforcement Transformation for Low-textured Scientific Sketch Image Retrieval
Studies augmentation with reinforcement transformation for retrieving low-textured scientific sketch images.
VTV-FM: Flow Matching through Variational Terminal-Velocity Closure
Derives missing terminal velocities by minimizing acceleration energy, enabling second-order flow matching with curved transport paths, consistent optimal-transport pairing, and learned acceleration targets.
Graph Learning from Label Proportions using Topology-Aware Pseudo Labeling and Aggregation
Extends learning from label proportions to graphs by generating topology-aware soft pseudo-labels through optimal transport and training graph neural networks from aggregate supervision.
ColdDDI: Evaluating Knowledge Utilization in Cold-Start Drug-Drug Interaction Prediction
Benchmarks cold-start drug–drug interaction prediction with mechanism-stratified splits and evidence interventions to distinguish access to biomedical knowledge from models’ actual use of it.
Physics-Refined Spatiotemporal Forecasting on Open-Boundary Hydrologic Graphs
Combines ghost-node proxies for unobserved boundary forcing with local and global physics refiners to stabilize autoregressive forecasting on open-boundary hydrologic graphs.
An ensemble-based network architecture search framework for 3D dose prediction in radiotherapy
Studies ensemble-based neural architecture search for predicting three-dimensional radiotherapy dose distributions, linking automated model design with a clinical treatment-planning prediction task.
Online Decision Trees for Varying Feature Spaces via Gradient-Based Surrogates
Develops online decision trees for varying feature spaces through gradient-based surrogate modeling, addressing prediction when the attributes available in a data stream change.
Online Learning for Wild Streaming Data with Delayed Feedback
Combines online Gaussian-copula alignment, uncertainty-calibrated geometric pseudo-labels, and dual-track learning to adapt to heterogeneous, incomplete, drifting data streams when ground-truth feedback arrives late.
Implicit Fine-tuning via Context Engineering: A Curriculum Learning Framework for Multimodal Entity Alignment
Relates context engineering to fine-tuning and uses curriculum-guided, confidence-adaptive prompts to align multimodal entities progressively from simpler to more complex evidence.
PSQE: A Theoretical-Practical Approach to Pseudo Seed Quality Enhancement for Unsupervised Multimodal Entity Alignment
Improves unsupervised multimodal entity alignment by refining pseudo-seed precision and balancing their graph coverage through multimodal information, clustering, and resampling.
Federated Latent Factor Learning for Privacy-Preserving Spatio-Temporal Signal Recovery
Recovers missing sensor signals through federated latent factor learning that exchanges gradients rather than raw readings and regularizes representations with spatial and temporal correlations.
SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL
Generates SQL from natural-language questions using a trained schema linker, schema-aware retrieval of examples, and Pareto-based selection among candidate queries.
MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery
Uses state-specific and state-invariant reinforcement-learning agents, a DAG generation policy, and factored actions to incrementally discover causal graph structures from observational data.
Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAG
Constructs query-specific evidence graphs by recovering missing relations from source text and selecting relevant facts jointly with existing knowledge-graph edges for question answering.
Boundary-Consistent Graph Neural Networks for Topological Flux Prediction
Models unobserved external forcing with ghost-node proxies and coupled boundary–interior fixed-point inference to make graph neural networks more consistent for fluid-network flux prediction.
A Novel Spatiotemporally-Regularized Latent Factorization of Tensors Model for Learning Accurate Dynamics from Temporal Sensing Networks
A spatiotemporally regularized tensor factorization model represents changing sensing-network dynamics by combining latent tensor representations with spatial and temporal structural constraints.
Federated Latent Factorization of Tensors for Privacy-Preserving Representation Learning to Large-Scale Dynamic Weighted Directed Network
FLFT learns latent representations of dynamic weighted directed networks through data-density-aware federated tensor factorization, combining local bias correction, privacy-preserving filling, and nonlinear interaction modeling.
Non-Gradient Hash Factor Learning for High-Dimensional and Incomplete Data Representation Learning
NGHF uses discrete differential evolution to optimize binary latent factors directly, learning representations of high-dimensional incomplete data without the quantization step used by continuous relaxations.
A Survey on Computational Pathology Foundation Models: Datasets, Adaptation Strategies, and Evaluation Tasks
This survey organizes computational pathology foundation models by pretraining datasets, adaptation strategies, and evaluation tasks, highlighting multimodal integration, domain variability, and gaps in standardized assessment.
SADD-RFCO: Semi-Supervised Anomalous Data Detection Based on Random Forest with Co-Training
SADD-RFCO partitions features into two views and co-trains random forests with iterative pseudo-labeling and soft voting to detect anomalies in partially labeled, contaminated data.
Multimetric Autoencoder for Representing High-Dimensional and Incomplete Data
MMA combines four autoencoders defined by different loss and regularization norms, using adaptive weighting to represent heterogeneous high-dimensional data with missing entries.
Large Language Model-Assisted Research Question Development in Public Health: A Case Study in the Special Supplemental Nutrition Program for Women, Infants, and Children
A controlled study evaluates GPT-4 and a scholarly search plugin for generating WIC policy research questions, comparing literature-informed prompting with prompts without literature context through expert assessment.
2025
Understanding Vulnerability Detection Difficulties, a New Metric and an Explanation
Examines vulnerability detection difficulties through a new evaluation metric and an explanatory analysis.
Link Completion for Dynamic Knowledge Graphs with Entity Drift
Investigates link completion in dynamic knowledge graphs whose entities drift over time, focusing on maintaining graph relationships as the represented entities evolve.
LHGEL: Large Heterogeneous Graph Ensemble Learning using Batch View Aggregation
LHGEL ensembles graph learners trained on sampled batch views, combining residual attention and diversity regularization to learn scalable representations of large heterogeneous graphs.
Topology-aware Neural Flux Prediction Guided by Physics
PhysicsNFP combines directional difference matrices with physical constraints on graph message passing to preserve high-frequency topological signals when predicting flows on directed networks.
HGEN: Heterogeneous Graph Ensemble Networks
HGEN ensembles heterogeneous-graph neural networks built from meta-paths and random dropping, using residual attention and correlation regularization to balance learner accuracy and representational diversity.
How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback
TCR-QF restores source-text context around knowledge-graph triples and iteratively adds query-relevant missing knowledge, addressing information loss in graph-augmented question answering.
A Novel Sparse Active Online Learning Framework for Fast and Accurate Streaming Anomaly Detection Over Data Streams
SAD combines sparse online feature selection with CUR-based active instance selection, using reconstruction residuals to score anomalies in evolving streams under computational and memory constraints.
Query-Driven Multimodal GraphRAG: Dynamic Local Knowledge Graph Construction for Online Reasoning
This framework constructs query-specific multimodal knowledge graphs through semantic graph patterns, multi-path retrieval, and on-demand information completion to support cross-modal question answering.
Metric-Agnostic Continual Learning for Sustainable Group Fairness
MacFRL reorders continual-learning tasks so a classifier learns from confident tasks before tackling larger distribution shifts, aiming to sustain group fairness with unlabeled data.
ℓ₁,∞-Mixed Norm Promoted Row Sparsity for Fast Online CUR Decomposition Learning in Varying Feature Spaces
SOOFS combines mixed-norm row sparsity with online CUR decomposition to select informative instances within sliding windows while learning from data streams with changing feature spaces.
Federated Projection Hamming Hash Latent Factor Learning Model
Introduces a federated latent factor learning model that combines projection operations and Hamming hashing to learn compact representations from distributed data sources.
SciTableQA: A Question-Answering Benchmark for Complex Scientific Tables
Introduces a benchmark of complex scientific tables with human-verified questions that test language models on cell selection and arithmetic reasoning across irregular table layouts.
Uncertainty-Aware Complex Scientific Table Data Extraction
Combines table structure recognition, optical character recognition, and conformal prediction to flag uncertain extractions and prioritize human verification of complex scientific tables.
Interpretable Individual Manatee Identification Using Sketch Images and Deep Neural Networks
Uses deep neural networks to localize distinctive scars and other markers in expert-drawn sketches, enabling interpretable matching and identification of individual manatees.
Multi-Modal Foundation Models for Computational Pathology: A Survey
Surveys computational pathology foundation models that combine histology images with language, knowledge graphs, or gene expression, organizing their datasets, downstream tasks, training methods, and evaluation challenges.
Online Outlier Detection in Open Feature Spaces
Learns an incrementally updated latent hypersphere from feature embeddings to detect outliers in data streams whose feature spaces change over time.
Online Learning from Mix-typed, Drifted, and Incomplete Streaming Features
Uses a copula-based latent representation, adaptive drift-detection windows, and geometric label propagation to learn from mixed-type streaming features when distributions shift and labels are incomplete.
A shaping two-stage anomaly data recovery method based on multi-norm joint optimization under energy internet
Recovers random and consecutive missing energy measurements through matrix reshaping, two-stage temporal reconstruction, and multi-norm optimization solved with an alternating-direction method.
Insulator defect detection from aerial images in adverse weather conditions
Combines image deraining and dehazing with an attention-enhanced YOLOv7 detector to identify insulator defects in aerial photographs captured under adverse weather.
Robust Low-Rank Latent Feature Analysis for Spatiotemporal Signal Recovery
Combines low-rank latent feature modeling, spatiotemporal regularization, and an outlier-resistant loss to recover missing sensor measurements from noisy wireless sensing networks.
2024
ℓ₁,₂-Norm and CUR Decomposition based Sparse Online Active Learning for Data Streams with Streaming Features
Uses mixed-norm online CUR decomposition to jointly select informative instances and stable features for sparse active learning in streams with evolving feature spaces.
HGDL: Heterogeneous Graph Label Distribution Learning
Combines meta-path topology homogenization with a topology-and-content-aware graph transformer to learn label distributions for nodes in heterogeneous graphs while preserving structural and semantic consistency.
Utilitarian Online Learning from Open-World Soft Sensing
Learns a universal representation for evolving soft-sensing features and balances prediction risk against abstention costs when previously unknown classes appear in streaming observations.
Fairness-Aware Streaming Feature Selection with Causal Graphs
Builds causal graphs around prediction labels and protected attributes to select streaming features while balancing predictive accuracy and fairness as features arrive over time.
Learning Gradual Typing Performance
Learns runtime models from dynamic type-check overheads to predict how type-annotation configurations affect gradual programs and support performance-aware migration between typing configurations.
GLDL: Graph Label Distribution Learning
Co-trains graph convolutional networks over instance and label relationships to learn node label distributions while jointly modeling dependencies among instances, labels, and their cross-relations.
MKG-FENN: A Multimodal Knowledge Graph Fused End-to-end Neural Network for Accurate Drug-Drug Interaction Prediction
MKG-FENN predicts drug–drug interaction events by extracting features from four complementary molecular and biomedical knowledge graphs and fusing them through an end-to-end neural network.
Robust Sparse Online Learning for Data Streams with Streaming Features
RSOL uses a mixed-norm regularizer and closed-form proximal updates to maintain sparse online predictors when features emerge or disappear from a data stream.
Multi-type load forecasting model based on random forest and density clustering with the influence of noise and load patterns
MLF-RFDC combines density-based noise detection, latent-factor data recovery, and random-forest forecasting to integrate multiple electrical load types while accounting for distinct consumption patterns.
Online Learning from Evolving Feature Spaces with Deep Variational Models
OLD3S learns shared latent representations and adapts model capacity online, transferring knowledge across evolving feature spaces while retaining information learned from previously observed features.
MMLF: Multi-Metric Latent Feature Analysis for High-Dimensional and Incomplete Data
MMLF adaptively ensembles six latent-factor models spanning different vector spaces and loss norms to represent heterogeneous, high-dimensional matrices with missing observations.
A Debiasing Autoencoder for Recommender System
AutoRec++ combines preprocessing and training bias corrections with mixed loss norms, addressing multiple sources of bias and outliers in autoencoder-based recommendation from user behavior data.
A Prediction-Sampling-Based Multilayer-Structured Latent Factor Model for Accurate Representation to High-Dimensional and Sparse Data
PMLF builds a multilayer latent-factor architecture that progressively supplements sparse matrices with synthetic entries, using prediction sampling and nonlinear activations to constrain the data-generation process.
2023
IKGN: Intention-aware Knowledge Graph Network for POI Recommendation
IKGN integrates visit histories, trajectories, and location categories into an intention-aware knowledge graph, combining attention-based propagation with sequential modeling for point-of-interest recommendation.
MMA: Multi-Metric-Autoencoder for Analyzing High-Dimensional and Incomplete Data
MMA combines four autoencoders with different loss and regularization norms through adaptive weighting, learning representations of heterogeneous high-dimensional data with incomplete observations.
Towards Utilitarian Online Learning – A Review of Online Algorithms in Open Feature Space
This survey organizes online learning in open feature spaces into a unified taxonomy, compares representative algorithms, and identifies application scenarios, limitations, and research directions.
Online Semi-Supervised Learning with Mix-Typed Streaming Features
OSLMF uses copula-based feature alignment and online neighborhood label propagation to learn from mixed-type, evolving feature spaces when only a subset of arriving instances is labeled.
Online Random Feature Forests for Learning in Varying Feature Spaces
ORF3V maintains an interpretable ensemble of feature-specific decision forests, updating and pruning compressed feature representations as variables appear or disappear in online data streams.
A Graph-Incorporated Latent Factor Analysis Model for High-Dimensional and Sparse Data
GLFA extracts hidden high-order interactions from sparse matrices as a graph and incorporates them into a recurrent latent-factor architecture for missing-entry prediction.
A Lightweight Dynamic Storage Algorithm With Adaptive Encoding for Energy Internet
LDSA-AE classifies energy-internet data by activity and adapts replication and erasure coding to balance distributed storage overhead, access latency, repair speed, and reliability.
BCTC-KSM: A blockchain-assisted threshold cryptography for key security management in power IoT data sharing
BCTC-KSM combines verifiable threshold secret sharing, blockchain records, and attribute-based access controls to manage encryption keys for cloud-stored power-IoT data shared among authorized participants.
A Double-Space and Double-Norm Ensembled Latent Factor Model for Highly Accurate Web Service QoS Prediction
D2E-LF ensembles inner-product and distance-based latent-factor predictors with mixed loss norms, capturing complementary characteristics of sparse web-service quality-of-service observations for missing-value prediction.
A Quantitative Risk Assessment Model for Distribution Cyber-Physical System Under Cyberattack
Combines Bayesian risk modeling, epidemic-style propagation, and optimal load shedding to assess how cyberattacks and device dependencies affect the security of distribution cyber-physical systems.
Privacy-Preserving Multi-Granular Federated Neural Architecture Search – A General Framework
Investigates multi-granular neural architecture search in federated settings, combining model selection across distributed datasets with the requirement to preserve the privacy of client data.
2022
Online Deep Learning from Doubly-Streaming Data
Learns a shared latent representation across evolving feature spaces while adapting neural network depth and parameters online to accommodate changes in the complexity of streaming data.
Online Sparse Streaming Feature Selection with Uncertainty
Estimates missing streaming features with latent factor analysis, then combines fuzzy logic and neighborhood rough sets to address uncertainty between imputed feature values and class labels.
AutoRec++: Incorporating Debias Methods Into Autoencoder-Based Recommender System
Combines preprocessing and training debiasing strategies within an autoencoder-based recommender to address biases in user behavior data without changing the underlying neural network architecture.
OR-AutoRec: An Outlier-Resilient Autoencoder-Based Recommendation Model
Uses a Cauchy-loss autoencoder to model user–item interactions while reducing the influence of outlier ratings and potentially malicious user behavior on the resulting recommendations.
Camouflaged Poisoning Attack on Graph Neural Networks
Generates camouflaged fake nodes and learned connections to poison graph neural networks for global or targeted misclassification without directly modifying the features of original graph nodes.
A Robust Latent Factor Analysis Model for Incomplete Data Recovery in Wireless Sensor Networks
Studies robust latent factor analysis for recovering incomplete wireless sensor network data, using latent representations to estimate missing measurements from the available sensor observations.
Toward Auto-Learning Hyperparameters for Deep Learning-Based Recommender Systems
Integrates differential evolution into recommender training to learn layer-specific learning rates and regularization coefficients automatically, reducing dependence on manually configured searches for these hyperparameters.
Quantitative combination load forecasting model based on forecasting error optimization
Combines a K-means and least-squares forecasting-error model with gene expression programming to incorporate uncertain load-data errors into quantitative prediction of electricity demand from observed data.
A Latent Factor Analysis-Based Approach to Online Sparse Streaming Feature Selection
Uses latent factor analysis to estimate missing values before selecting features online, enabling feature selection as incomplete feature columns arrive for a fixed set of instances.
A Data-Characteristic-Aware Latent Factor Model for Web Services QoS Prediction
Uses density-peaks clustering over latent user and service representations to identify neighborhoods and noise, adapting quality-of-service prediction to the characteristics of sparse observations from web services.
A Posterior-neighborhood-regularized Latent Factor Model for Highly Accurate Web Service QoS Prediction
Builds user and service neighborhoods from initially learned latent factors, then uses those posterior neighborhoods to regularize quality-of-service predictions without requiring additional geographical information.
2021
An Ensemble Latent Factor Model for Highly Accurate Web Service QoS Prediction
Studies an ensemble of latent factor models for predicting missing web-service quality-of-service values, combining multiple predictors to model sparse observations of interactions between users and services.
Online Learning in Variable Feature Spaces with Mixed Data
Models dependencies among mixed-type streaming features with a Gaussian copula, allowing an online learner to transfer information across feature spaces as features appear and disappear.
Interpretable Minority Synthesis for Imbalanced Classification
Uses a Bayesian-regularized generative adversarial network to synthesize minority-class examples with interpretable feature dependencies specified through human input, supporting classification when labeled data are imbalanced.
Unsupervised Lifelong Learning with Curricula
Initializes lifelong learning with one labeled task, then orders unlabeled tasks by their distance to accumulated knowledge to reduce negative transfer.
Online Learning in Variable Feature Spaces under Incomplete Supervision
Combines a universal feature space with sparse manifold regularization to update online classifiers when feature sets vary and supervision is available only intermittently.
Toward Wiser Funding Allocation with Bayesian Networks
Examines the use of Bayesian networks to inform funding-allocation decisions, representing uncertain dependencies relevant to distributing limited resources among competing alternatives.
Toward Mining Capricious Data Streams: A Generative Approach
Uses a generative graph to reconstruct related features in a universal space, allowing online learning from streams whose features can appear or disappear without predefined rules.
A Deep Latent Factor Model for High-Dimensional and Sparse Matrices in Recommender Systems
Builds a deep recommender by sequentially connecting latent factor models through nonlinear activations, learning from high-dimensional sparse rating matrices with computation that scales with depth.
2020
Active Learning with Multi-Granular Graph Auto-Encoder
Combines node attributes and network topology through a multi-granular graph autoencoder to select informative instances for labeling, with a query strategy designed to tolerate noisy labels.
On Partial Multi-Task Learning
Learns a shared latent feature space across related tasks and uses a generative graph to recover missing representations, enabling predictions from only partially collected task examples.
Online Learning to Accelerate Neural Network Inference with Traveling Classifiers
Trains traveling classifiers online from consecutive neural-network layers to identify redundant computation after deployment and produce earlier predictions as incoming data reveal application-specific patterns.
Learning with Partial Multi-Outlooks
Uses cross-outlook feature relationships to build a shared repository that reconstructs missing representations, enabling prediction when instances are observed through only some heterogeneous views.
Deep Matrix Tri-Factorization: Mining Vertex-wise Interactions in Multi-Space Attributed Graphs
Learns nonlinear combinations of heterogeneous vertex features through deep matrix tri-factorization, extracting higher-level representations to model interactions between vertices in multi-space attributed graphs.
2019
Online Feature Selection with Capricious Streaming Features: A General Framework
Completes missing entries in newly arriving features with latent factor analysis, allowing existing online feature-selection algorithms to process capricious streams containing incomplete feature observations.
Generating Precise Error Specifications for C: A Zero Shot Learning Approach
Combines source-code analysis with transfer learning and project-specific features to infer C error-return specifications, requiring no manual labels from users of previously unseen projects.
Online Learning from Capricious Data Streams: A Generative Approach
Constructs a universal feature space with a generative graphical model so online learners can transfer previously learned patterns to new features in arbitrarily changing data streams.
A Data-Aware Latent Factor Model for Web Service QoS Prediction
Integrates density-peak clustering into a latent factor model to identify service neighborhoods and unreliable quality-of-service measurements, predicting missing values without requiring additional geographic information.
2018
Supervised Data Synthesizing and Evolving – A Framework for Real-World Traffic Crash Severity Classification
Studies a supervised data-synthesis and evolution framework for traffic-crash severity classification, connecting generated training examples with predictive models for real-world transportation records.
Online Streaming Feature Selection via Conditional Independence
Applies three layers of conditional-independence filtering to approximate a Markov blanket, removing irrelevant and redundant features as candidate variables arrive in a stream.
No matching publications
Try another topic, keyword, or year.