Search Results for author:
Found 69 papers, 13 papers with code
Distillation-Driven Diffusion Model for Multi-Scale MRI Super-Resolution: Make 1.5T MRI Great Again
Specifically, the student model refines the 7T SR task with steps, leveraging feature maps from the inference phase of the teacher model as guidance, aiming to allow the student model to achieve progressively 7T SR performance with a smaller, deployable model size.
Generating with Fairness: A Modality-Diffused Counterfactual Framework for Incomplete Multimodal Recommendations
However, two significant gaps persist: 1) the difficulty in accurately generating missing data due to the limited ability to capture modality distributions; and 2) the critical but overlooked visibility bias, where items with missing modalities are more likely to be disregarded due to the prioritization of items' multimodal data over user preference alignment.
Attribution for Enhanced Explanation with Transferable Adversarial eXploration
The interpretability of deep neural networks is crucial for understanding model decisions in various applications, including computer vision.
LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input Contexts
To bridge the gap between current RRG models and the clinical demands in practice, we first develop a data generation pipeline to create a new MIMIC-RG4 dataset, which considers four common radiology report drafting scenarios and has perfectly corresponded input and output.
Navigating Towards Fairness with Data Selection
Machine learning algorithms often struggle to eliminate inherent data biases, particularly those arising from unreliable labels, which poses a significant challenge in ensuring fairness.
Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods
This paper explores the ability of Graph Neural Networks (GNNs) in learning various forms of information for link prediction, alongside a brief review of existing link prediction methods.
Ranked #1 on
Link Property Prediction
on ogbl-citation2
RED: Residual Estimation Diffusion for Low-Dose PET Sinogram Reconstruction
From the perspective of diffusion mechanism, RED uses the residual between sinograms to replace Gaussian noise in diffusion process, respectively sets the low-dose and full-dose sinograms as the starting point and endpoint of reconstruction.
Feasibility Study of a Diffusion-Based Model for Cross-Modal Generation of Knee MRI from X-ray: Integrating Radiographic Feature Information
Through ablation studies, we further validate that integrating supplementary patient-specific information, beyond what X-rays alone can provide, enhances the accuracy and clinical relevance of the generated MRI, which underscores the potential of leveraging external patient-specific information to improve the MRI generation.
Trust-informed Decision-Making Through An Uncertainty-Aware Stacked Neural Networks Framework: Case Study in COVID-19 Classification
This study presents an uncertainty-aware stacked neural networks model for the reliable classification of COVID-19 from radiological images.
IVGF: The Fusion-Guided Infrared and Visible General Framework
Besides, the attention-guided fusion module is proposed for effectively fusing by exploring the complementary information of two modalities.
Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editing
GE-AdvGAN, a recent method for transferable adversarial attacks, is based on this principle.
Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack
Given the essence of adversarial attacks is to impair model integrity with minimal noise on original samples, exploring avenues to maximize the utility of such perturbations is imperative.
TransFeat-TPP: An Interpretable Deep Covariate Temporal Point Processes
The classical temporal point process (TPP) constructs an intensity function by taking the occurrence times into account.
ReDistill: Residual Encoded Distillation for Peak Memory Reduction
Reducing peak memory, which is the maximum memory consumed during the execution of a neural network, is critical to deploy neural networks on edge devices with limited memory budget.
Interpretable Robotic Manipulation from Language
Natural language, moreover, serves as the primary medium through which humans acquire new knowledge, presenting a potentially intuitive bridge for translating concepts understandable by humans into formats that can be learned by machines.
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
Recent studies highlighted a practical setting of unsupervised anomaly detection (UAD) that builds a unified model for multi-class images.
Ranked #2 on
Anomaly Detection
on VisA
Causal Learning for Trustworthy Recommender Systems: A Survey
However, emerging vulnerabilities in RS have catalyzed a paradigm shift towards Trustworthy RS (TRS).
Semantic-Preserving Feature Partitioning for Multi-View Ensemble Learning
Addressing these challenges, multi-view ensemble learning (MEL) has emerged as a transformative approach, with feature partitioning (FP) playing a pivotal role in constructing artificial views for MEL.
SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Search
In this paper, we demonstrate that by using multi-objective search algorithms paired with lightly trained predictors, we can efficiently search for both the sub-network architecture and the corresponding quantization policy and outperform their respective baselines across different performance objectives such as accuracy, model size, and latency.
The Innovation-to-Occupations Ontology: Linking Business Transformation Initiatives to Occupations and Skills
The fast adoption of new technologies forces companies to continuously adapt their operations making it harder to predict workforce requirements.
ACGAN-GNNExplainer: Auxiliary Conditional Generative Explainer for Graph Neural Networks
Graph neural networks (GNNs) have proven their efficacy in a variety of real-world applications, but their underlying mechanisms remain a mystery.
Full-resolution Lung Nodule Segmentation from Chest X-ray Images using Residual Encoder-Decoder Networks
The proposed algorithm achieved excellent generalization results against an external dataset with sensitivity of 77% at a false positive rate of 7. 6.
Ethical ChatGPT: Concerns, Challenges, and Commandments
Large language models, e. g. ChatGPT are currently contributing enormously to make artificial intelligence even more popular, especially among the general population.
Confidence-Driven Deep Learning Framework for Early Detection of Knee Osteoarthritis
Knee Osteoarthritis (KOA) is a prevalent musculoskeletal disorder that severely impacts mobility and quality of life, particularly among older adults.
Meta-learning approaches for few-shot learning: A survey of recent advances
Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction.
Key-Exchange Convolutional Auto-Encoder for Data Augmentation in Early Knee Osteoarthritis Detection
These findings highlight the potential of KECAE as a robust tool for augmenting medical datasets in early KOA detection.
Genetic Imitation Learning by Reward Extrapolation
Imitation learning demonstrates remarkable performance in various domains.
Explaining Imitation Learning through Frames
As one of the prevalent methods to achieve automation systems, Imitation Learning (IL) presents a promising performance in a wide range of domains.
GANExplainer: GAN-based Graph Neural Networks Explainer
With the rapid deployment of graph neural networks (GNNs) based techniques into a wide range of applications such as link prediction, node classification, and graph classification the explainability of GNNs has become an indispensable component for predictive and trustworthy decision-making.
DGNet: Distribution Guided Efficient Learning for Oil Spill Image Segmentation
In this paper, we develop an effective segmentation framework named DGNet, which performs oil spill segmentation by incorporating the intrinsic distribution of backscatter values in SAR images.
Domain Generalization by Learning and Removing Domain-specific Features
With the images output by the encoder-decoder network, another classifier is designed to learn the domain-invariant features to conduct image classification.
Ranked #24 on
Domain Generalization
on PACS
Self-Attentive Pooling for Efficient Deep Learning
With the aggressive down-sampling of the activation maps in the initial layers (providing up to 22x reduction in memory consumption), our approach achieves 1. 43% higher test accuracy compared to SOTA techniques with iso-memory footprints.
Instance Image Retrieval by Learning Purely From Within the Dataset
Although achieving promising results, this approach is restricted by two issues: 1) the domain gap between benchmark datasets and the dataset of a given retrieval task; 2) the required auxiliary dataset cannot be readily obtained.
Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour
Furthermore, we design a novel Interaction-Aware Transformer (IAT) to dynamically learn the graph-level representation of social behaviours and update the node-level representation, guided by our proposed interaction-aware self-attention mechanism.
De-biased Representation Learning for Fairness with Unreliable Labels
In other words, the fair pre-processing methods ignore the discrimination encoded in the labels either during the learning procedure or the evaluation stage.
A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics
Graph neural networks (GNNs) have demonstrated a significant boost in prediction performance on graph data.
Detection of magnetohydrodynamic waves by using machine learning
Identification of different types of MHD waves is an important and challenging task in such complex wave patterns.
Incident duration prediction using a bi-level machine learning framework with outlier removal and intra-extra joint optimisation
Predicting the duration of traffic incidents is a challenging task due to the stochastic nature of events.
Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds
We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range.
Evolutionary dynamics of zero-determinant strategies in repeated multiplayer games
Here, we use a newly proposed state-clustering method to theoretically analyze the evolutionary dynamics of two representative ZD strategies: generous ZD strategies and extortionate ZD strategies.
State-clustering method of payoff computation in repeated multiplayer games
In this paper, we propose a new method, namely, the state-clustering method to calculate the long-term payoffs in repeated games.
Local Patch Network with Global Attention for Infrared Small Target Detection
A local patch network (LPNet) with global attention is proposed in this paper to detect small targets by jointly considering the global and local properties of infrared small target images.
Bias-Tolerant Fair Classification
Therefore, we propose a Bias-TolerantFAirRegularizedLoss (B-FARL), which tries to regain the benefits using data affected by label bias and selection bias.
Imitation Learning: Progress, Taxonomies and Challenges
Imitation learning aims to extract knowledge from human experts' demonstrations or artificially created agents in order to replicate their behaviors.
Facilitating Machine Learning Model Comparison and Explanation Through A Radial Visualisation
The dependence of ML models with dynamic number of features is encoded into the structure of visualisation, where ML models and their dependent features are directly revealed from related line connections.
Variational Co-embedding Learning for Attributed Network Clustering
Recent works for attributed network clustering utilize graph convolution to obtain node embeddings and simultaneously perform clustering assignments on the embedding space.
Boosted Genetic Algorithm using Machine Learning for traffic control optimization
Lastly, we propose a new algorithm BGA-ML combining the GA algorithm and the extreme-gradient decision-tree, which is the best performing regressor, together in a single optimization framework.
Novel structural evolution of several nanolaminate Mn+1AXn (n=1, 2, 3, etc.) ceramics under pressure from first principles
We did extensive research for the typical nanolaminate Mn+1AXn (n=1, 2, 3) ceramics focusing on the structural stability, the phase transition pressure of Ti2GaN (160 GPa) is far higher than that of Zr2GaN (92 GPa), meaning the strong M dependence of the same group, whereas Zr2AlN (98 GPa) has similar value with that of Zr2GaN, meaning the weak A dependence.
Materials Science
Structured Context Enhancement Network for Mouse Pose Estimation
However, quantifying mouse behaviours from videos or images remains a challenging problem, where pose estimation plays an important role in describing mouse behaviours.
Deep-HOSeq: Deep Higher Order Sequence Fusion for Multimodal Sentiment Analysis
In this research, we first propose a common network to discover both intra-modal and inter-modal dynamics by utilizing basic LSTMs and tensor based convolution networks.
A Multi-Task Learning Neural Network for Emotion-Cause Pair Extraction
In this paper, we propose a multi-task neural network to perform emotion-cause pair extraction in a unified model.
Examination of Community Sentiment Dynamics due to COVID-19 Pandemic: A Case Study from A State in Australia
In this paper, we exploit the massive text data posted by Twitter users to analyse the sentiment dynamics of people living in the state of New South Wales (NSW) in Australia during the pandemic period.
Utilizing machine learning to prevent water main breaks by understanding pipeline failure drivers
Data61 and Western Water worked collaboratively to apply engineering expertise and Machine Learning tools to find a cost-effective solution to the pipe failure problem in the region west of Melbourne, where on average 400 water main failures occur per year.
An improved online learning algorithm for general fuzzy min-max neural network
This paper proposes an improved version of the current online learning algorithm for a general fuzzy min-max neural network (GFMM) to tackle existing issues concerning expansion and contraction steps as well as the way of dealing with unseen data located on decision boundaries.
Scalable Inference for Nonparametric Hawkes Process Using Pólya-Gamma Augmentation
In this paper, we consider the sigmoid Gaussian Hawkes process model: the baseline intensity and triggering kernel of Hawkes process are both modeled as the sigmoid transformation of random trajectories drawn from Gaussian processes (GP).
Machine Learning in/for Blockchain: Future and Challenges
Machine learning and blockchain are two of the most noticeable technologies in recent years.
Efficient EM-Variational Inference for Hawkes Process
In classical Hawkes process, the baseline intensity and triggering kernel are assumed to be a constant and parametric function respectively, which limits the model flexibility.
An Effective Multi-Resolution Hierarchical Granular Representation based Classifier using General Fuzzy Min-Max Neural Network
Motivated by the practical demands for simplification of data towards being consistent with human thinking and problem solving as well as tolerance of uncertainty, information granules are becoming important entities in data processing at different levels of data abstraction.
Graph-Based Decoding Model for Functional Alignment of Unaligned fMRI Data
Aggregating multi-subject functional magnetic resonance imaging (fMRI) data is indispensable for generating valid and general inferences from patterns distributed across human brains.
A Unified Neural Network Model for Geolocating Twitter Users
Locations of social media users are important to many applications such as rapid disaster response, targeted advertisement, and news recommendation.
A Graph-theoretic Summary Evaluation for ROUGE
ROUGE is one of the first and most widely used evaluation metrics for text summarization.
Summarization Evaluation in the Absence of Human Model Summaries Using the Compositionality of Word Embeddings
We present a new summary evaluation approach that does not require human model summaries.
A Semantically Motivated Approach to Compute ROUGE Scores
ROUGE is one of the first and most widely used evaluation metrics for text summarization.
AMC: Attention guided Multi-modal Correlation Learning for Image Search
According to the intent of query, attention mechanism can be introduced to adaptively balance the importance of different modalities.
Appraising UMLS Coverage for Summarizing Medical Evidence
When making clinical decisions, practitioners need to rely on the most relevant evidence available.
Infinite Hidden Semi-Markov Modulated Interaction Point Process
The proposed approach can simultaneously model both the observations and arrival times of temporal events, and determine the number of latent states from data.
Stochastic Patching Process
Due to constraints of partition strategy, existing models may cause unnecessary dissections in sparse regions when fitting data in dense regions.
On Improving Informativity and Grammaticality for Multi-Sentence Compression
In this paper, we propose an effective approach to enhance the word graph-based MSC and tackle the issue that most of the state-of-the-art MSC approaches are confronted with: i. e., improving both informativity and grammaticality at the same time.
Stable Learning in Coding Space for Multi-Class Decoding and Its Extension for Multi-Class Hypothesis Transfer Learning
Many prevalent multi-class classification approaches can be unified and generalized by the output coding framework which usually consists of three phases: (1) coding, (2) learning binary classifiers, and (3) decoding.
