Search Results for author:
Found 114 papers, 42 papers with code
N-Gram Nearest Neighbor Machine Translation
Nearest neighbor machine translation augments the Autoregressive Translation~(AT) with $k$-nearest-neighbor retrieval, by comparing the similarity between the token-level context representations of the target tokens in the query and the datastore.
Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense
Experiments on two public datasets show that ClusterAttack can effectively degrade the performance of FedRec systems while circumventing many defense methods, and UNION can improve the resistance of the system against various untargeted attacks, including our ClusterAttack.
Progressive Knowledge Transfer Based on Human Visual Perception Mechanism for Perceptual Quality Assessment of Point Clouds
In this paper, a progressive knowledge transfer based on human visual perception mechanism for perceptual quality assessment of point clouds (PKT-PCQA) is proposed.
Nested Named Entity Recognition from Medical Texts: An Adaptive Shared Network Architecture with Attentive CRF
Recognizing useful named entities plays a vital role in medical information processing, which helps drive the development of medical area research.
Medical Named Entity Recognition
named-entity-recognition
+2
One Person, One Model--Learning Compound Router for Sequential Recommendation
The core idea of CANet is to route the input user behaviors with a light-weighted router module.
Searching Dense Point Correspondences via Permutation Matrix Learning
In response, this paper presents a novel end-to-end learning-based method to estimate the dense correspondence of 3D point clouds, in which the problem of point matching is formulated as a zero-one assignment problem to achieve a permutation matching matrix to implement the one-to-one principle fundamentally.
CU-Net: LiDAR Depth-Only Completion With Coupled U-Net
We find that existing depth-only methods can obtain satisfactory results in the areas where the measurement points are almost accurate and evenly distributed (denoted as normal areas), while the performance is limited in the areas where the foreground and background points are overlapped due to occlusion (denoted as overlap areas) and the areas where there are no measurement points around (denoted as blank areas) since the methods have no reliable input information in these areas.
Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play
We first design a SQL-to-text model conditioned on a sampled goal query, which represents a user's intent, that then converses with a text-to-SQL semantic parser to generate new interactions.
Hierarchical Graph Transformer with Adaptive Node Sampling
The Transformer architecture has achieved remarkable success in a number of domains including natural language processing and computer vision.
Model Inversion Attacks against Graph Neural Networks
One famous privacy attack against data analysis models is the model inversion attack, which aims to infer sensitive data in the training dataset and leads to great privacy concerns.
Cross-scale Attention Guided Multi-instance Learning for Crohn's Disease Diagnosis with Pathological Images
Multi-instance learning (MIL) is widely used in the computer-aided interpretation of pathological Whole Slide Images (WSIs) to solve the lack of pixel-wise or patch-wise annotations.
Causal Machine Learning: A Survey and Open Problems
Causal Machine Learning (CausalML) is an umbrella term for machine learning methods that formalize the data-generation process as a structural causal model (SCM).
Evaluating Self-Supervised Learning for Molecular Graph Embeddings
Graph Self-Supervised Learning (GSSL) paves the way for learning graph embeddings without expert annotation, which is particularly impactful for molecular graphs since the number of possible molecules is enormous and labels are expensive to obtain.
Retrieval-enhanced Graph Neural Networks for Graph Property Prediction
In GraphRetrieval, similar training graphs associated with their ground-truth labels are retrieved as an enhancement to be jointly utilized with the input graph representation to complete various graph property predictive tasks.
Context-Aware Video Reconstruction for Rolling Shutter Cameras
Then, a refinement scheme is proposed to guide the GS frame synthesis along with bilateral occlusion masks to produce high-fidelity GS video frames at arbitrary times.
Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification
Existing studies in this task attach more attention to the sequence modeling of sentences while largely ignoring the rich domain-invariant semantics embedded in graph structures (i. e., the part-of-speech tags and dependency relations).
Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) predicts sentiment polarity towards a specific aspect in the given sentence.
Asynchronous Decentralized Federated Learning for Collaborative Fault Diagnosis of PV Stations
Therefore, federated learning can be exploited to train a collaborative fault diagnosis model.
A Comparative Study of Deep Reinforcement Learning-based Transferable Energy Management Strategies for Hybrid Electric Vehicles
Different exploration methods of DRL, including adding action space noise and parameter space noise, are compared against each other in the transfer learning process in this work.
Ligandformer: A Graph Neural Network for Predicting Compound Property with Robust Interpretation
Robust and efficient interpretation of QSAR methods is quite useful to validate AI prediction rationales with subjective opinion (chemist or biologist expertise), understand sophisticated chemical or biological process mechanisms, and provide heuristic ideas for structure optimization in pharmaceutical industry.
Low-Rank and Row-Sparse Decomposition for Joint DOA Estimation and Distorted Sensor Detection
Distorted sensors could occur randomly and may lead to the breakdown of a sensor array system.
Graph Convolution-Based Deep Reinforcement Learning for Multi-Agent Decision-Making in Mixed Traffic Environments
Several GRL approaches are summarized and implemented in the proposed framework.
Relational Memory Augmented Language Models
We present a memory-augmented approach to condition an autoregressive language model on a knowledge graph.
Deep Unified Representation for Heterogeneous Recommendation
Recommendation system has been a widely studied task both in academia and industry.
Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction
One aspect that has been obviated so far, is the fact that how we represent the skeletal pose has a critical impact on the prediction results.
ProtGNN: Towards Self-Explaining Graph Neural Networks
In this work, we propose Prototype Graph Neural Network (ProtGNN), which combines prototype learning with GNNs and provides a new perspective on the explanations of GNNs.
Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation
We further propose a two-stage knowledge distillation method to improve the efficiency of the large PLM-based news recommendation model while maintaining its performance.
Contrastive Cross-domain Recommendation in Matching
Cross-domain recommendation (CDR) aims to provide better recommendation results in the target domain with the help of the source domain, which is widely used and explored in real-world systems.
Nonlinear Tensor Ring Network
Experimental results demonstrate the effectiveness and superiority of the proposed NTRN for image classification using two basic neural networks, LeNet-5 and VGG-11 on three datasets, viz.
Perceptual Quality Assessment of Colored 3D Point Clouds
In this work, we first build a large 3D point cloud database for subjective and objective quality assessment of point clouds.
Motif-based Graph Self-Supervised Learning for Molecular Property Prediction
To bridge this gap, we propose Motif-based Graph Self-supervised Learning (MGSSL) by introducing a novel self-supervised motif generation framework for GNNs.
DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis
Text-to-image synthesis refers to generating an image from a given text description, the key goal of which lies in photo realism and semantic consistency.
SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation
Specifically, we first encode user/item reviews via BERT and propose a light-weighted sentiment learner to extract semantic features of each review.
LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching
In order to overcome this problem and boost the performance of attention mechanism, we propose a novel dynamic re-read attention, which can pay close attention to one small region of sentences at each step and re-read the important parts for better sentence representations.
The CORSMAL benchmark for the prediction of the properties of containers
In this paper, we present a range of methods and an open framework to benchmark acoustic and visual perception for the estimation of the capacity of a container, and the type, mass, and amount of its content.
Decision-Making Technology for Autonomous Vehicles Learning-Based Methods, Applications and Future Outlook
Autonomous vehicles have a great potential in the application of both civil and military fields, and have become the focus of research with the rapid development of science and economy.
Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation
Hence, the key is to make full use of rich interaction information among streamers, users, and products.
GraphMI: Extracting Private Graph Data from Graph Neural Networks
Then we design a graph auto-encoder module to efficiently exploit graph topology, node attributes, and target model parameters for edge inference.
Hybrid attention network based on progressive embedding scale-context for crowd counting
In this paper, we propose a Hybrid Attention Network (HAN) by employing Progressive Embedding Scale-context (PES) information, which enables the network to simultaneously suppress noise and adapt head scale variation.
Causal Effect Inference for Structured Treatments
We address the estimation of conditional average treatment effects (CATEs) for structured treatments (e. g., graphs, images, texts).
Counterfactual Data Augmentation for Neural Machine Translation
We propose a data augmentation method for neural machine translation.
Estimating Fund-Raising Performance for Start-up Projects from a Market Graph Perspective
Usually, this prediction is always with great challenges to making a comprehensive understanding of both the start-up project and market environment.
Cardiac Functional Analysis with Cine MRI via Deep Learning Reconstruction
To the best of our knowledge, this is the first work to evaluate the cine MRI with deep learning reconstruction for cardiac function analysis and compare it with other conventional methods.
A Survey of Knowledge Tracing
The recent COVID-19 epidemic has triggered the outbreak of online education, which has enabled both students and teachers to learn and teach at home.
XCrossNet: Feature Structure-Oriented Learning for Click-Through Rate Prediction
Motivated by this, we propose a novel Extreme Cross Network, abbreviated XCrossNet, which aims at learning dense and sparse feature interactions in an explicit manner.
Pretraining the Noisy Channel Model for Task-Oriented Dialogue
Direct decoding for task-oriented dialogue is known to suffer from the explaining-away effect, manifested in models that prefer short and generic responses.
Ranked #2 on
End-To-End Dialogue Modelling
on MULTIWOZ 2.0
PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features
Spherical Voxel Convolution and Point Re-sampling are proposed to extract rotation invariant features for each point.
NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application
However, existing language models are pre-trained and distilled on general corpus like Wikipedia, which has some gaps with the news domain and may be suboptimal for news intelligence.
A Hybrid Bandit Model with Visual Priors for Creative Ranking in Display Advertising
Creative plays a great important role in e-commerce for exhibiting products.
Improving Accuracy and Diversity in Matching of Recommendation with Diversified Preference Network
In this paper, we propose a novel Heterogeneous graph neural network framework for diversified recommendation (GraphDR) in matching to improve both recommendation accuracy and diversity.
Scenario Generation for Cooling, Heating, and Power Loads Using Generative Moment Matching Networks
Scenario generations of cooling, heating, and power loads are of great significance for the economic operation and stability analysis of integrated energy systems.
Learning the Implicit Semantic Representation on Graph-Structured Data
Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole, while the implicit semantic associations behind highly complex interactions of graphs are largely unexploited.
Quality meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing
In this paper, we study a novel model-agnostic CAT problem, where we aim to propose a flexible framework that can adapt to different cognitive models.
Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction
In the Click-Through Rate (CTR) prediction scenario, user's sequential behaviors are well utilized to capture the user interest in the recent literature.
Early systems change necessary for catalyzing long-term sustainability in a post-2030 agenda
Progress to-date towards the Sustainable Development Goals (SDGs) has fallen short of expectations and is unlikely to fully meet 2030 targets.
Reduced Reference Perceptual Quality Model and Application to Rate Control for 3D Point Cloud Compression
In rate-distortion optimization, the encoder settings are determined by maximizing a reconstruction quality measure subject to a constraint on the bit rate.
An Odor Labeling Convolutional Encoder-Decoder for Odor Sensing in Machine Olfaction
In this paper, we proposed an odor labeling convolutional encoder-decoder (OLCE) for odor identification in machine olfaction.
Sampling-Decomposable Generative Adversarial Recommender
The GAN-style recommenders (i. e., IRGAN) addresses the challenge by learning a generator and a discriminator adversarially, such that the generator produces increasingly difficult samples for the discriminator to accelerate optimizing the discrimination objective.
End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining
Second, we propose to predict the quadrilateral bounding box in the local region by regressing the four corners of the license plate to robustly detect oblique license plates.
An Investigation on Different Underlying Quantization Schemes for Pre-trained Language Models
Recently, pre-trained language models like BERT have shown promising performance on multiple natural language processing tasks.
Unsupervised Point Cloud Pre-Training via Occlusion Completion
We find that even when we construct a single pre-training dataset (from ModelNet40), this pre-training method improves accuracy across different datasets and encoders, on a wide range of downstream tasks.
Ranked #4 on
Point Cloud Segmentation
on PointCloud-C
3D Point Cloud Linear Classification
Point Cloud Classification
+4
Pre-Training by Completing Point Clouds
There has recently been a flurry of exciting advances in deep learning models on point clouds.
Conditional Uncorrelation and Efficient Non-approximate Subset Selection in Sparse Regression
By the proposed method, the computational complexity is reduced from $O(\frac{1}{6}{k^3}+mk^2+mkd)$ to $O(\frac{1}{6}{k^3}+\frac{1}{2}mk^2)$ for each candidate subset in sparse regression.
An Investigation on Deep Learning with Beta Stabilizer
It is concluded that beta stabilizer parameters can reduce the sensitivity of learning rate with almost the same performance on DNN with relu activation function and LSTM.
Future Vector Enhanced LSTM Language Model for LVCSR
For the speech recognition rescoring, although the proposed LSTM LM obtains very slight gains, the new model seems obtain the great complementary with the conventional LSTM LM.
A Study on Effects of Implicit and Explicit Language Model Information for DBLSTM-CTC Based Handwriting Recognition
Deep Bidirectional Long Short-Term Memory (D-BLSTM) with a Connectionist Temporal Classification (CTC) output layer has been established as one of the state-of-the-art solutions for handwriting recognition.
ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction
Here we propose a novel framework called Active Semi-supervised Graph Neural Network (ASGN) by incorporating both labeled and unlabeled molecules.
A Survey on Sensor Technologies for Unmanned Ground Vehicles
Unmanned ground vehicles have a huge development potential in both civilian and military fields, and have become the focus of research in various countries.
HGKT: Introducing Hierarchical Exercise Graph for Knowledge Tracing
To solve the above problems, we propose a hierarchical graph knowledge tracing model called HGKT to explore the latent hierarchical relations between exercises.
Learning the Compositional Visual Coherence for Complementary Recommendations
Towards this end, in this paper, we propose a novel Content Attentive Neural Network (CANN) to model the comprehensive compositional coherence on both global contents and semantic contents.
IROS 2019 Lifelong Robotic Vision Challenge -- Lifelong Object Recognition Report
This report summarizes IROS 2019-Lifelong Robotic Vision Competition (Lifelong Object Recognition Challenge) with methods and results from the top $8$ finalists (out of over~$150$ teams).
Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition
We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for classification and sequence labelling) to jointly extract dialogue states.
An end-to-end CNN framework for polarimetric vision tasks based on polarization-parameter-constructing network
Pixel-wise operations between polarimetric images are important for processing polarization information.
A Survey on Contextual Embeddings
Contextual embeddings, such as ELMo and BERT, move beyond global word representations like Word2Vec and achieve ground-breaking performance on a wide range of natural language processing tasks.
SketchyCOCO: Image Generation from Freehand Scene Sketches
We introduce the first method for automatic image generation from scene-level freehand sketches.
Ranked #2 on
Sketch-to-Image Translation
on SketchyCOCO
Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction
Specifically, we build a Multi-Relational Item Graph (MRIG) based on all behavior sequences from all sessions, involving target and auxiliary behavior types.
Domain Adaption for Knowledge Tracing
We refer to this problem as domain adaptation for knowledge tracing (DAKT) which contains two aspects: (1) how to achieve great knowledge tracing performance in each domain.
Deep Technology Tracing for High-tech Companies
Technological change and innovation are vitally important, especially for high-tech companies.
Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach
However, few of them take into account the inherent decision-making process between investors and crowdfunding dynamics.
A Comprehensive Study and Comparison of Core Technologies for MPEG 3D Point Cloud Compression
Point cloud based 3D visual representation is becoming popular due to its ability to exhibit the real world in a more comprehensive and immersive way.
Estimating Early Fundraising Performance of Innovations via Graph-based Market Environment Model
In the crowdfunding market, the early fundraising performance of the project is a concerned issue for both creators and platforms.
Hyperbolic Graph Neural Networks
Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise.
Long-term Joint Scheduling for Urban Traffic
Recently, the traffic congestion in modern cities has become a growing worry for the residents.
Neural Cognitive Diagnosis for Intelligent Education Systems
Cognitive diagnosis is a fundamental issue in intelligent education, which aims to discover the proficiency level of students on specific knowledge concepts.
Multi-Task Self-Supervised Learning for Disfluency Detection
The pre-trained network is then fine-tuned using human-annotated disfluency detection training data.
Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective
In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction.
Ranked #6 on
Graph Regression
on Lipophilicity
EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction
In EERNN, we simply summarize each student's state into an integrated vector and trace it with a recurrent neural network, where we design a bidirectional LSTM to learn the encoding of each exercise's content.
Chinese Embedding via Stroke and Glyph Information: A Dual-channel View
Recent studies have consistently given positive hints that morphology is helpful in enriching word embeddings.
Promotion of Answer Value Measurement with Domain Effects in Community Question Answering Systems
Existing solutions mainly exploit the syntactic or semantic correlation between a question and its related answers (Q&A), where the multi-facet domain effects in CQA are still underexplored.
Explainable Fashion Recommendation: A Semantic Attribute Region Guided Approach
When making cloth decisions, people usually show preferences for different semantic attributes (e. g., the clothes with v-neck collar).
Ranked #2 on
Recommendation Systems
on Amazon Fashion
(using extra training data)
Enhancing Item Response Theory for Cognitive Diagnosis
However, traditional IRT ignores the rich information in question texts, cannot diagnose knowledge concept proficiency, and it is inaccurate to diagnose the parameters for the questions which only appear several times.
Transcribing Content from Structural Images with Spotlight Mechanism
Then, we decide "what-to-write" by developing a GRU based network with the spotlight areas for transcribing the content accordingly.
MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network
Recently, the Network Representation Learning (NRL) techniques, which represent graph structure via low-dimension vectors to support social-oriented application, have attracted wide attention.
QuesNet: A Unified Representation for Heterogeneous Test Questions
Then we propose a two-level hierarchical pre-training algorithm to learn better understanding of test questions in an unsupervised way.
Exploiting Cognitive Structure for Adaptive Learning
Although it is well known that modeling the cognitive structure including knowledge level of learners and knowledge structure (e. g., the prerequisite relations) of learning items is important for learning path recommendation, existing methods for adaptive learning often separately focus on either knowledge levels of learners or knowledge structure of learning items.
Quaternion Knowledge Graph Embeddings
In this work, we move beyond the traditional complex-valued representations, introducing more expressive hypercomplex representations to model entities and relations for knowledge graph embeddings.
Ranked #4 on
Link Prediction
on FB15k
Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds
In this paper we will use deep learning based medical image segmentation as a vehicle and demonstrate that interestingly, machine and human view the compression quality differently.
Insertion-based Decoding with automatically Inferred Generation Order
Conventional neural autoregressive decoding commonly assumes a fixed left-to-right generation order, which may be sub-optimal.
Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution
Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown.
Skeptical Deep Learning with Distribution Correction
Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data.
Random Occlusion-recovery for Person Re-identification
As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera.
Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors
In this paper, we propose a novel Behavior-Intensive Neural Network (BINN) for next-item recommendation by incorporating both users' historical stable preferences and present consumption motivations.
Mining Evidences for Concept Stock Recommendation
We investigate the task of mining relevant stocks given a topic of concern on emerging capital markets, for which there is lack of structural understanding.
Learning Domain Representation for Multi-Domain Sentiment Classification
It is useful to leveraging data available for all existing domains to enhance performance on different domains.
Constrained Graph Variational Autoencoders for Molecule Design
Graphs are ubiquitous data structures for representing interactions between entities.
Sentence-State LSTM for Text Representation
Bi-directional LSTMs are a powerful tool for text representation.
Ranked #10 on
Part-Of-Speech Tagging
on Penn Treebank
Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples
Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently.
On Modular Training of Neural Acoustics-to-Word Model for LVCSR
Finally, modules are integrated into an acousticsto-word model (A2W) and jointly optimized using acoustic data to retain the advantage of sequence modeling.
Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks
In this work, we for the first time investigate the multi-factor adversarial attack problem in practical model optimized deep learning systems by jointly considering the DNN model-reshaping (e. g. HashNet based deep compression) and the input perturbations.
Divide and Recombine for Large and Complex Data: Model Likelihood Functions using MCMC
The density parameters are estimated by fitting the density to MCMC draws from each subset DM likelihood function, and then the fitted densities are recombined.
SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction
First, due to the lack of explicit sentiment links in mainstream social networks, we establish a labeled heterogeneous sentiment dataset which consists of users' sentiment relation, social relation and profile knowledge by entity-level sentiment extraction method.
Applying High-Resolution Visible Imagery to Satellite Melt Pond Fraction Retrieval: A Neural Network Approach
It is important to retrieve accurate melt pond fraction (MPF) from satellite data for Arctic research.
An Adaptive Amoeba Algorithm for Shortest Path Tree Computation in Dynamic Graphs
When the edge weight changes, the proposed algorithm can recognize the affected vertices and reconstruct them spontaneously.
