Search Results for author:
Found 95 papers, 35 papers with code
Optimal Stochastic Strongly Convex Optimization with a Logarithmic Number of Projections
We consider stochastic strongly convex optimization with a complex inequality constraint.
N$^3$LARS: Minimum Redundancy Maximum Relevance Feature Selection for Large and High-dimensional Data
We propose a feature selection method that finds non-redundant features from a large and high-dimensional data in nonlinear way.
Consistent Collective Matrix Completion under Joint Low Rank Structure
We address the collective matrix completion problem of jointly recovering a collection of matrices with shared structure from partial (and potentially noisy) observations.
Convex Factorization Machine for Regression
We propose the convex factorization machine (CFM), which is a convex variant of the widely used Factorization Machines (FMs).
A Survey of Signed Network Mining in Social Media
Many real-world relations can be represented by signed networks with positive and negative links, as a result of which signed network analysis has attracted increasing attention from multiple disciplines.
Scaling Submodular Maximization via Pruned Submodularity Graphs
We propose a new random pruning method (called "submodular sparsification (SS)") to reduce the cost of submodular maximization.
Hierarchical Attention Network for Action Recognition in Videos
Understanding human actions in wild videos is an important task with a broad range of applications.
Streaming Recommender Systems
The increasing popularity of real-world recommender systems produces data continuously and rapidly, and it becomes more realistic to study recommender systems under streaming scenarios.
Ultra High-Dimensional Nonlinear Feature Selection for Big Biological Data
However, sophisticated learning models are computationally unfeasible for data with millions of features.
Attributed Network Embedding for Learning in a Dynamic Environment
To our best knowledge, we are the first to tackle this problem with the following two challenges: (1) the inherently correlated network and node attributes could be noisy and incomplete, it necessitates a robust consensus representation to capture their individual properties and correlations; (2) the embedding learning needs to be performed in an online fashion to adapt to the changes accordingly.
Hyper-Laplacian Regularized Unidirectional Low-Rank Tensor Recovery for Multispectral Image Denoising
Recent low-rank based matrix/tensor recovery methods have been widely explored in multispectral images (MSI) denoising.
Weighted Low-rank Tensor Recovery for Hyperspectral Image Restoration
To overcome these limitations, in this work, we propose a unified low-rank tensor recovery model for comprehensive HSI restoration tasks, in which non-local similarity between spectral-spatial cubic and spectral correlation are simultaneously captured by 3-order tensors.
Ranked #12 on
Hyperspectral Image Denoising
on ICVL-HSI-Gaussian50
Transformed Low-Rank Model for Line Pattern Noise Removal
This paper addresses the problem of line pattern noise removal from a single image, such as rain streak, hyperspectral stripe and so on.
Achieving Strong Regularization for Deep Neural Networks
L1 and L2 regularizers are critical tools in machine learning due to their ability to simplify solutions.
Contextual and Position-Aware Factorization Machines for Sentiment Classification
While existing machine learning models have achieved great success for sentiment classification, they typically do not explicitly capture sentiment-oriented word interaction, which can lead to poor results for fine-grained analysis at the snippet level (a phrase or sentence).
Disentangling Aspect and Opinion Words in Target-based Sentiment Analysis using Lifelong Learning
Stage one extracts/groups the target-related words (call t-words) for a given target.
Abstract Meaning Representation for Paraphrase Detection
Abstract Meaning Representation (AMR) parsing aims at abstracting away from the syntactic realization of a sentence, and denote only its meaning in a canonical form.
Target-Sensitive Memory Networks for Aspect Sentiment Classification
In MNs, attention mechanism plays a crucial role in detecting the sentiment context for the given target.
Document Modeling with External Attention for Sentence Extraction
Document modeling is essential to a variety of natural language understanding tasks.
Rain Streak Removal for Single Image via Kernel Guided CNN
Then, our framework starts with learning the motion blur kernel, which is determined by two factors including angle and length, by a plain neural network, denoted as parameter net, from a patch of the texture component.
Zero-shot User Intent Detection via Capsule Neural Networks
User intent detection plays a critical role in question-answering and dialog systems.
Sequenced-Replacement Sampling for Deep Learning
We propose sequenced-replacement sampling (SRS) for training deep neural networks.
Adversarial Sampling and Training for Semi-Supervised Information Retrieval
To solve the problems at the same time, we propose an adversarial sampling and training framework to learn ad-hoc retrieval models with implicit feedback.
Gradient-Coherent Strong Regularization for Deep Neural Networks
However, we observe that imposing strong L1 or L2 regularization with stochastic gradient descent on deep neural networks easily fails, which limits the generalization ability of the underlying neural networks.
JIM: Joint Influence Modeling for Collective Search Behavior
This assumption is unrealistic as there are many correlated events in the real world which influence each other and thus, would pose a joint influence on the user search behavior rather than posing influence independently.
Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System
To improve the quality and retrieval performance of the generated questions, we make two major improvements: 1) To better encode the semantics of ill-formed questions, we enrich the representation of questions with character embedding and the recent proposed contextual word embedding such as BERT, besides the traditional context-free word embeddings; 2) To make it capable to generate desired questions, we train the model with deep reinforcement learning techniques that considers an appropriate wording of the generation as an immediate reward and the correlation between generated question and answer as time-delayed long-term rewards.
Jointly Modeling Hierarchical and Horizontal Features for Relational Triple Extraction
In this work, we first introduce the hierarchical dependency and horizontal commonality between the two levels, and then propose an entity-enhanced dual tagging framework that enables the triple extraction (TE) task to utilize such interactions with self-learned entity features through an auxiliary entity extraction (EE) task, without breaking the joint decoding of relational triples.
Classical Chinese Sentence Segmentation for Tomb Biographies of Tang Dynasty
Chinese characters that are and are not followed by a punctuation mark are classified into two categories.
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction
Extracting relational triples from unstructured text is crucial for large-scale knowledge graph construction.
Ranked #5 on
Relation Extraction
on NYT11-HRL
Self-paced Ensemble for Highly Imbalanced Massive Data Classification
To tackle this problem, we conduct deep investigations into the nature of class imbalance, which reveals that not only the disproportion between classes, but also other difficulties embedded in the nature of data, especially, noises and class overlapping, prevent us from learning effective classifiers.
GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
In this paper, we propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method.
Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion
In experiments, we achieve state-of-the-art performance on three benchmarks and a zero-shot dataset for link prediction, with highlights of inference costs reduced by 1-2 orders of magnitude compared to a textual encoding method.
Ranked #4 on
Link Prediction
on UMLS
Unsupervised Hyperspectral Mixed Noise Removal Via Spatial-Spectral Constrained Deep Image Prior
Recently, convolutional neural network (CNN)-based methods are proposed for hyperspectral images (HSIs) denoising.
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler
This makes MESA generally applicable to most of the existing learning models and the meta-sampler can be efficiently applied to new tasks.
ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction
Distantly Supervised Relation Extraction (DSRE) has proven to be effective to find relational facts from texts, but it still suffers from two main problems: the wrong labeling problem and the long-tail problem.
Robust early-learning: Hindering the memorization of noisy labels
The \textit{early stopping} method therefore can be exploited for learning with noisy labels.
Ranked #32 on
Image Classification
on mini WebVision 1.0
(ImageNet Top-1 Accuracy metric)
Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection
AA-HGNN utilizes an active learning framework to enhance learning performance, especially when facing the paucity of labeled data.
Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks
We study the problem of incorporating prior knowledge into a deep Transformer-based model, i. e., Bidirectional Encoder Representations from Transformers (BERT), to enhance its performance on semantic textual matching tasks.
Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation
Existing deep learning-based image deraining methods have achieved promising performance for synthetic rainy images, typically rely on the pairs of sharp images and simulated rainy counterparts.
Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimation
Based on it, a more robust doubly robust (MRDR) estimator has been proposed to further reduce its variance while retaining its double robustness.
Self-Supervised Nonlinear Transform-Based Tensor Nuclear Norm for Multi-Dimensional Image Recovery
Recently, transform-based tensor nuclear norm minimization methods are considered to capture low-rank tensor structures to recover third-order tensors in multi-dimensional image processing applications.
Image Restoration for Remote Sensing: Overview and Toolbox
Additionally, this review paper accompanies a toolbox to provide a platform to encourage interested students and researchers in the field to further explore the restoration techniques and fast-forward the community.
Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching between Parts and Words
Specifically, we first segment the point clouds into parts, and then leverage optimal transport method to match parts and words in an optimized feature space, where each part is represented by aggregating features of all points within it and each word is abstracted by its contextual information.
Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction
Aspect-level sentiment classification (ALSC) aims at identifying the sentiment polarity of a specified aspect in a sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
Orthogonal Graph Neural Networks
Graph neural networks (GNNs) have received tremendous attention due to their superiority in learning node representations.
CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks
In this paper, we investigate GNNs from the lens of weight and feature loss landscapes, i. e., the loss changes with respect to model weights and node features, respectively.
IMBENS: Ensemble Class-imbalanced Learning in Python
imbalanced-ensemble, abbreviated as imbens, is an open-source Python toolbox for leveraging the power of ensemble learning to address the class imbalance problem.
Handling Inter-class and Intra-class Imbalance in Class-imbalanced Learning
Class-imbalance is a common problem in machine learning practice.
Physically Disentangled Intra- and Inter-Domain Adaptation for Varicolored Haze Removal
Consequently, we perform inter-domain adaptation between the synthetic and real images by mutually exchanging the background and other two components.
Event-based Video Reconstruction via Potential-assisted Spiking Neural Network
We propose a novel Event-based Video reconstruction framework based on a fully Spiking Neural Network (EVSNN), which utilizes Leaky-Integrate-and-Fire (LIF) neuron and Membrane Potential (MP) neuron.
Computational Efficiency
Event-Based Video Reconstruction
+2
Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition
The proposed framework consists of i) federated learning for data privacy, and ii) adversarial training at the training stage and randomisation at the testing stage for model robustness.
Climate Change & Computer Audition: A Call to Action and Overview on Audio Intelligence to Help Save the Planet
We categorise potential computer audition applications according to the five elements of earth, water, air, fire, and aether, proposed by the ancient Greeks in their five element theory; this categorisation serves as a framework to discuss computer audition in relation to different ecological aspects.
Unsupervised Image Deraining: Optimization Model Driven Deep CNN
Consequently, we design an optimization model-driven deep CNN in which the unsupervised loss function of the optimization model is enforced on the proposed network for better generalization.
Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis
Respiratory sound classification is an important tool for remote screening of respiratory-related diseases such as pneumonia, asthma, and COVID-19.
A Unified Collaborative Representation Learning for Neural-Network based Recommender Systems
On the other hand, ME models directly employ inner products as a default loss function metric that cannot project users and items into a proper latent space, which is a methodological disadvantage.
The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure
The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space.
A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection
Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances.
Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning
Our main idea is to design the multi-action-branch reward estimation and policy-weighted reward aggregation for stabilized training.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Knowledge Transfer For On-Device Speech Emotion Recognition with Neural Structured Learning
Our experiments demonstrate that training a lightweight SER model on the target dataset with speech samples and graphs can not only produce small SER models, but also enhance the model performance compared to models with speech samples only and those using classic transfer learning strategies.
Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity
In addition, considering that the existing real rain datasets are of low quality, either small scale or downloaded from the internet, we collect a real large-scale dataset under various rainy kinds of weather that contains high-resolution rainy images.
Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables
Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation learning, while being more interpretable in their predictions.
FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification
Weakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data.
One-shot Machine Teaching: Cost Very Few Examples to Converge Faster
Then, relying on the surjective mapping from the teaching set to the parameter, we develop a design strategy of the optimal teaching set under appropriate settings, of which two popular efficiency metrics, teaching dimension and iterative teaching dimension are one.
Both Diverse and Realism Matter: Physical Attribute and Style Alignment for Rainy Image Generation
To solve this dilemma, we propose a physical alignment and controllable generation network (PCGNet) for diverse and realistic rain generation.
A Comprehensive Survey on Heart Sound Analysis in the Deep Learning Era
Deep learning has been successfully applied to heart sound analysis in the past years.
Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow
To handle the practical optical flow under real foggy scenes, in this work, we propose a novel unsupervised cumulative domain adaptation optical flow (UCDA-Flow) framework: depth-association motion adaptation and correlation-alignment motion adaptation.
Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flow
In motion adaptation, we utilize the flow consistency knowledge to align the cross-domain optical flows into a motion-invariance common space, where the optical flow from clean weather is used as the guidance-knowledge to obtain a preliminary optical flow for adverse weather.
A Two-Stage Real Image Deraining Method for GT-RAIN Challenge CVPR 2023 Workshop UG$^{\textbf{2}}$+ Track 3
Secondly, a transformer-based single image deraining network Uformer is implemented to pre-train on large real rain dataset and then fine-tuned on pseudo GT to further improve image restoration.
UADB: Unsupervised Anomaly Detection Booster
This is a challenging task given the heterogeneous model structures and assumptions adopted by existing UAD methods.
Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning
Recent works have shown the potential of diffusion models in computer vision and natural language processing.
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning
However, constrained by the limited quality of the offline dataset, its performance is often sub-optimal.
1st Solution Places for CVPR 2023 UG$^2$+ Challenge Track 2.2-Coded Target Restoration through Atmospheric Turbulence
We subsequently select the sharpest set of registered frames by employing a frame selection approach based on image sharpness, and average them to produce an image that is largely free of geometric distortion, albeit with blurriness.
1st Solution Places for CVPR 2023 UG$^{\textbf{2}}$+ Challenge Track 2.1-Text Recognition through Atmospheric Turbulence
In this technical report, we present the solution developed by our team VIELab-HUST for text recognition through atmospheric turbulence in Track 2. 1 of the CVPR 2023 UG$^{2}$+ challenge.
A Survey on Evaluation of Large Language Models
Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications.
Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs.
From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal
Learning-based image deraining methods have made great progress.
Careful at Estimation and Bold at Exploration
In prior work, it has been shown that policy-based exploration is beneficial for continuous action space in deterministic policy reinforcement learning(DPRL).
Learning Generalizable Agents via Saliency-Guided Features Decorrelation
Our experimental results demonstrate that SGFD can generalize well on a wide range of test environments and significantly outperforms state-of-the-art methods in handling both task-irrelevant variations and task-relevant variations.
B-Spine: Learning B-Spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation
In this paper, we propose B-Spine, a novel deep learning pipeline to learn B-spline curve representation of the spine and estimate the Cobb angles for spinal curvature estimation from low-quality X-ray images.
A Survey on Data Augmentation in Large Model Era
Leveraging large models, these data augmentation techniques have outperformed traditional approaches.
Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow
In appearance adaptation, we employ the intrinsic image decomposition to embed the auxiliary daytime image and the nighttime image into a reflectance-aligned common space.
EPSD: Early Pruning with Self-Distillation for Efficient Model Compression
Instead of a simple combination of pruning and SD, EPSD enables the pruned network to favor SD by keeping more distillable weights before training to ensure better distillation of the pruned network.
STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition
Speech contains rich information on the emotions of humans, and Speech Emotion Recognition (SER) has been an important topic in the area of human-computer interaction.
Copyright Protection in Generative AI: A Technical Perspective
We examine from two distinct viewpoints: the copyrights pertaining to the source data held by the data owners and those of the generative models maintained by the model builders.
Contrastive Diffuser: Planning Towards High Return States via Contrastive Learning
Applying diffusion models in reinforcement learning for long-term planning has gained much attention recently.
Transductive Reward Inference on Graph
In this study, we present a transductive inference approach on that reward information propagation graph, which enables the effective estimation of rewards for unlabelled data in offline reinforcement learning.
ScreenAgent: A Vision Language Model-driven Computer Control Agent
Additionally, we construct the ScreenAgent Dataset, which collects screenshots and action sequences when completing a variety of daily computer tasks.
Investigating Out-of-Distribution Generalization of GNNs: An Architecture Perspective
These insights have empowered us to develop a novel GNN backbone model, DGAT, designed to harness the robust properties of both graph self-attention mechanism and the decoupled architecture.
The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
In this work, we conduct extensive empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems on leaking the private retrieval database.
DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
In the development stage, DS-Agent follows the CBR framework to structure an automatic iteration pipeline, which can flexibly capitalize on the expert knowledge from Kaggle, and facilitate consistent performance improvement through the feedback mechanism.
JSTR: Joint Spatio-Temporal Reasoning for Event-based Moving Object Detection
In spatial reasoning stage, we project the compensated events into the same image coordinate, discretize the timestamp of events to obtain a time image that can reflect the motion confidence, and further segment the moving object through adaptive threshold on the time image.
Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow
In this work, we bring the event as a bridge between RGB and LiDAR, and propose a novel hierarchical visual-motion fusion framework for scene flow, which explores a homogeneous space to fuse the cross-modal complementary knowledge for physical interpretation.
GT-Rain Single Image Deraining Challenge Report
This report reviews the results of the GT-Rain challenge on single image deraining at the UG2+ workshop at CVPR 2023.
HiTRANS: A Hierarchical Transformer Network for Nested Named Entity Recognition
Specifically, we first utilize a two-phase module to generate span representations by aggregating context information based on a bottom-up and top-down transformer network.
