Search Results for author:
Found 270 papers, 62 papers with code
A Three-step Method for Multi-Hop Inference Explanation Regeneration
Then, a selection module is employed to choose those most relative facts in an autoregressive manner, giving a preliminary order for the retrieved facts.
Building Goal-oriented Document-grounded Dialogue Systems
In this paper, we describe our systems for solving the two Doc2Dial shared task: knowledge identification and response generation.
Domain-specific knowledge distillation yields smaller and better models for conversational commerce
We demonstrate that knowledge distillation can be used not only to reduce model size, but to simultaneously adapt a contextual language model to a specific domain.
SemEval-2022 Task 8: Multilingual news article similarity
Thousands of new news articles appear daily in outlets in different languages.
PaLI-X: On Scaling up a Multilingual Vision and Language Model
We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture.
CONA: A novel CONtext-Aware instruction paradigm for communication using large language model
We introduce CONA, a novel context-aware instruction paradigm for effective knowledge dissemination using generative pre-trained transformer (GPT) models.
Text Generation with Speech Synthesis for ASR Data Augmentation
In this work, we explore text augmentation for ASR using large-scale pre-trained neural networks, and systematically compare those to traditional text augmentation methods.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Self-Supervised Instance Segmentation by Grasping
Leveraging this insight, we learn a grasp segmentation model to segment the grasped object from before and after grasp images.
Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN
Existing state-of-the-art methods are often unable to capture meaningful uncertainty in challenging or ambiguous scenes, and as such can cause critical errors in high-performance applications.
Transformer-based models and hardware acceleration analysis in autonomous driving: A survey
The paper also highlights the challenges, trends, and current insights in Transformer-based models, addressing their hardware deployment and acceleration issues within the context of long-term autonomous driving applications.
EEGSN: Towards Efficient Low-latency Decoding of EEG with Graph Spiking Neural Networks
A vast majority of spiking neural networks (SNNs) are trained based on inductive biases that are not necessarily a good fit for several critical tasks that require low-latency and power efficiency.
The Future of ChatGPT-enabled Labor Market: A Preliminary Study
To this end, in this paper, we introduce a preliminary data-driven study on the future of ChatGPT-enabled labor market from the view of Human-AI Symbiosis instead of Human-AI Confrontation.
Head-tail Loss: A simple function for Oriented Object Detection and Anchor-free models
However, for the second point, the minimum distance between the prediction and either the head or tail of the groundtruth is used.
FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead
We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI).
DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution
Moreover, DisC-Diff leverages a disentangled multi-stream network to fully exploit complementary information from multi-contrast MRI, improving model interpretation under multiple conditions of multi-contrast inputs.
CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis
Diffusion model has emerged as an effective technique for image synthesis by modelling complex and variable data distributions.
Detecting Everything in the Open World: Towards Universal Object Detection
In this paper, we formally address universal object detection, which aims to detect every scene and predict every category.
ScribbleSeg: Scribble-based Interactive Image Segmentation
We hope this could serve as a more powerful and general solution for interactive segmentation.
Open-vocabulary Panoptic Segmentation with Embedding Modulation
Open-vocabulary image segmentation is attracting increasing attention due to its critical applications in the real world.
Knowledge-augmented Few-shot Visual Relation Detection
Inspired by this, we devise a knowledge-augmented, few-shot VRD framework leveraging both textual knowledge and visual relation knowledge to improve the generalization ability of few-shot VRD.
Statistical Inference with Stochastic Gradient Methods under $φ$-mixing Data
In this paper, we propose a mini-batch SGD estimator for statistical inference when the data is $\phi$-mixing.
Uniformity Testing over Hypergrids with Subcube Conditioning
We give an algorithm for testing uniformity of distributions supported on hypergrids $[m]^n$, which makes $\tilde{O}(\text{poly}(m)\sqrt{n}/\epsilon^2)$ queries to a subcube conditional sampling oracle.
Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignment
Entity alignment (EA) for knowledge graphs (KGs) plays a critical role in knowledge engineering.
The most probable dynamics of receptor-ligand binding on cell membrane
We consider the dynamics of a receptor binding to a ligand on the cell membrane, where the receptor and ligand perform different motions and are thus modeled by stochastic differential equations with Gaussian noise or non-Gaussian noise.
3D Molecular Generation via Virtual Dynamics
Extensive experiment results on pocket-based molecular generation demonstrate that VD-Gen can generate novel 3D molecules to fill the target pocket cavity with high binding affinities, significantly outperforming previous baselines.
Combinatorial Inference on the Optimal Assortment in Multinomial Logit Models
Assortment optimization has received active explorations in the past few decades due to its practical importance.
A Framework of Transaction Packaging in High-throughput Blockchains
We develop a model of coordination and allocation of decentralized multi-sided markets, in which our theoretical analysis is promisingly optimizing the decentralized transaction packaging process at high-throughput blockchains or Web 3. 0 platforms.
Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation
In this paper, we study the application of Test-time domain adaptation in semantic segmentation (TTDA-Seg) where both efficiency and effectiveness are crucial.
Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent
With the fast development of big data, it has been easier than before to learn the optimal decision rule by updating the decision rule recursively and making online decisions.
Hyperspherical Quantization: Toward Smaller and More Accurate Models
Model quantization enables the deployment of deep neural networks under resource-constrained devices.
FreeEnricher: Enriching Face Landmarks without Additional Cost
To evaluate our method, we manually label the dense landmarks on 300W testset.
Interpretable Node Representation with Attribute Decoding
We further propose a new learning model, interpretable NOde Representation with Attribute Decoding (NORAD).
Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization
Recent research in robust optimization has shown an overfitting-like phenomenon in which models trained against adversarial attacks exhibit higher robustness on the training set compared to the test set.
Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledge
Extensive experiments demonstrate that PICSO can dramatically outperform the original PLMs and the other knowledge and synonym injection models on four different similarity-oriented tasks.
NeurIPS 2022 Competition: Driving SMARTS
The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.
Active Relation Discovery: Towards General and Label-aware Open Relation Extraction
Open Relation Extraction (OpenRE) aims to discover novel relations from open domains.
Self-Attentive Sequential Recommendation with Cheap Causal Convolutions
We evaluate the effectiveness of the proposed model in terms of both accurate and calibrated sequential recommendation.
Teacher-Student Architecture for Knowledge Learning: A Survey
To tackle this issue, Teacher-Student architectures were first utilized in knowledge distillation, where simple student networks can achieve comparable performance to deep teacher networks.
Dissecting Deep Metric Learning Losses for Image-Text Retrieval
In the event that the gradients are not integrable to a valid loss function, we implement our proposed objectives such that they would directly operate in the gradient space instead of on the losses in the embedding space.
Ranked #7 on
Cross-Modal Retrieval
on Flickr30k
Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction
With the development of pre-trained language models, many prompt-based approaches to data-efficient knowledge graph construction have been proposed and achieved impressive performance.
Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study
This paper presents an empirical study to build relation extraction systems in low-resource settings.
Distributed Estimation and Inference for Semi-parametric Binary Response Models
The development of modern technology has enabled data collection of unprecedented size, which poses new challenges to many statistical estimation and inference problems.
WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environments
It provides realistic 3D environments of variable complexity, various tasks, and multiple modes of interaction, where agents can learn to perceive 3D environments, navigate and plan, compete and cooperate in a human-like manner.
Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction
3D bounding boxes are a widespread intermediate representation in many computer vision applications.
MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text
While language Models store a massive amount of world knowledge implicitly in their parameters, even very large models often fail to encode information about rare entities and events, while incurring huge computational costs.
PaLI: A Jointly-Scaled Multilingual Language-Image Model
PaLI generates text based on visual and textual inputs, and with this interface performs many vision, language, and multimodal tasks, in many languages.
Ranked #1 on
Image Captioning
on nocaps out-of-domain
PreSTU: Pre-Training for Scene-Text Understanding
The ability to recognize and reason about text embedded in visual inputs is often lacking in vision-and-language (V&L) models, perhaps because V&L pre-training methods have often failed to include such an ability as their training objective.
MaXM: Towards Multilingual Visual Question Answering
Visual Question Answering (VQA) has been primarily studied through the lens of the English language.
Deep Baseline Network for Time Series Modeling and Anomaly Detection
By using this deep network, we can easily locate the baseline position and then provide reliable and interpretable anomaly detection result.
Majority Vote for Distributed Differentially Private Sign Selection
Simulation studies are conducted to demonstrate the effectiveness of our proposed method.
Two-stage Hypothesis Tests for Variable Interactions with FDR Control
In many scenarios such as genome-wide association studies where dependences between variables commonly exist, it is often of interest to infer the interaction effects in the model.
DP$^2$-VAE: Differentially Private Pre-trained Variational Autoencoders
Similar to other differentially private (DP) learners, the major challenge for DPGM is also how to achieve a subtle balance between utility and privacy.
Delta Hedging Liquidity Positions on Automated Market Makers
The dominant measure of loss in a Liquidity Position is Impermanent Loss.
Gradient-based Bi-level Optimization for Deep Learning: A Survey
Bi-level optimization, especially the gradient-based category, has been widely used in the deep learning community including hyperparameter optimization and meta knowledge extraction.
Fairness-aware Network Revenue Management with Demand Learning
Motivated by these practical needs, this paper studies the price-based network revenue management problem with both demand learning and fairness concern about the consumption across different resources.
Mitigating Data Heterogeneity in Federated Learning with Data Augmentation
Federated Learning (FL) is a prominent framework that enables training a centralized model while securing user privacy by fusing local, decentralized models.
Robust One Round Federated Learning with Predictive Space Bayesian Inference
In contrast, our method performs the aggregation on the predictive posteriors, which are typically easier to approximate owing to the low-dimensionality of the output space.
Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Process
We present Federated Bayesian Neural Regression (FedBNR), an algorithm that learns a scalable stand-alone global federated GP that respects clients' privacy.
ReCo: A Dataset for Residential Community Layout Planning
In order to address the issues and advance a benchmark dataset for various intelligent spatial design and analysis applications in the development of smart city, we introduce Residential Community Layout Planning (ReCo) Dataset, which is the first and largest open-source vector dataset related to real-world community to date.
Unbiased Implicit Feedback via Bi-level Optimization
Recent works reveal a huge gap between the implicit feedback and user-item relevance due to the fact that implicit feedback is also closely related to the item exposure.
Neural 3D Reconstruction in the Wild
We are witnessing an explosion of neural implicit representations in computer vision and graphics.
Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset
Research in massively multilingual image captioning has been severely hampered by a lack of high-quality evaluation datasets.
All You May Need for VQA are Image Captions
Visual Question Answering (VQA) has benefited from increasingly sophisticated models, but has not enjoyed the same level of engagement in terms of data creation.
Memory Bounds for Continual Learning
We make novel uses of communication complexity to establish that any continual learner, even an improper one, needs memory that grows linearly with $k$, strongly suggesting that the problem is intractable.
FocalClick: Towards Practical Interactive Image Segmentation
To make the model work with preexisting masks, we formulate a sub-task termed Interactive Mask Correction, and propose Progressive Merge as the solution.
Ranked #1 on
Interactive Segmentation
on GrabCut
(using extra training data)
Optimization of Directional Landmark Deployment for Visual Observer on SE(3)
An optimization method is proposed in this paper for novel deployment of given number of directional landmarks (location and pose) within a given region in the 3-D task space.
Multi-modal learning for predicting the genotype of glioma
In this study, we propose a multi-modal learning framework using three separate encoders to extract features of focal tumor image, tumor geometrics and global brain networks.
Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey
However, the temporal information embedded in the dynamic graphs brings new challenges in analyzing and deploying them.
Latent-Variable Advantage-Weighted Policy Optimization for Offline RL
Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions.
Coverage Optimization of Camera Network for Continuous Deformable Object
To reduce the computational complexity, some feature points are carefully selected representing the continuous deformation process, and the visual coverage for the deformable object is transferred to cover the specific feature points.
PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks
With the increasing abundance of pretrained models in recent years, the problem of selecting the best pretrained checkpoint for a particular downstream classification task has been gaining increased attention.
AutoMO-Mixer: An automated multi-objective Mixer model for balanced, safe and robust prediction in medicine
Accurately identifying patient's status through medical images plays an important role in diagnosis and treatment.
On Digital Subcarrier Multiplexing under A Bandwidth Limitation and ASE Noise
We show that digital subcarrier multiplexing (DSM) systems require much greater complexity for Nyquist pulse shaping than single-carrier (SC) systems, and it is a misconception that both systems use the same bandwidth when using the same pulse shaping.
Proportional Fairness in Federated Learning
With the increasingly broad deployment of federated learning (FL) systems in the real world, it is critical but challenging to ensure fairness in FL, i. e. reasonably satisfactory performances for each of the numerous diverse clients.
Ontology-enhanced Prompt-tuning for Few-shot Learning
Specifically, we develop the ontology transformation based on the external knowledge graph to address the knowledge missing issue, which fulfills and converts structure knowledge to text.
S2MS: Self-Supervised Learning Driven Multi-Spectral CT Image Enhancement
In S2MS framework, both the input and output labels are noisy images.
Collaborative learning of images and geometrics for predicting isocitrate dehydrogenase status of glioma
Further, the collaborative learning model achieves better performance than either the CNN or the GNN alone.
Generalized DataWeighting via Class-Level Gradient Manipulation
To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.
Interval-valued q-Rung Orthopair Fuzzy Choquet Integral Operators and Its Application in Group Decision Making
It is more flexible for decision makers to evaluate by interval-valued q-rung orthopair fuzzy set (IVq-ROFS), which offers fuzzy decision-making more applicational space.
Leveraging Intrinsic Gradient Information for Further Training of Differentiable Machine Learning Models
Designing models that produce accurate predictions is the fundamental objective of machine learning (ML).
Fairness-aware Online Price Discrimination with Nonparametric Demand Models
To handle this general class, we propose a soft fairness constraint and develop the dynamic pricing policy that achieves $\tilde{O}(T^{4/5})$ regret.
On the Complexity of Dynamic Submodular Maximization
We study dynamic algorithms for the problem of maximizing a monotone submodular function over a stream of $n$ insertions and deletions.
Generalized Data Weighting via Class-level Gradient Manipulation
To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.
Brain-inspired feature exaggeration in generative replay for continual learning
The catastrophic forgetting of previously learnt classes is one of the main obstacles to the successful development of a reliable and accurate generative continual learning model.
Active Learning for Contextual Search with Binary Feedbacks
In particular, for a sequence of arriving context vectors, with each context associated with an underlying value, the decision-maker either makes a query at a certain point or skips the context.
AutoMO-Mixer: An automated multi-objective multi-layer perspecton Mixer model for medical image based diagnosis
The experimental study demonstrated that AutoMO-Mixer can obtain better performance compared with Mixer and CNN.
MOBA: Multi-teacher Model Based Reinforcement Learning
Results show that, compared with SOTA model-free methods, our method can improve the data efficiency and system performance by up to 75% and 10%, respectively.
PAC-Bayes Information Bottleneck
Then, we build an IIW-based information bottleneck on the trade-off between accuracy and information complexity of NNs, namely PIB.
Deep Learning based Model-free Robust Load Restoration to Enhance Bulk System Resilience with Wind Power Penetration
This paper proposes a new deep learning (DL) based model-free robust method for bulk system on-line load restoration with high penetration of wind power.
Risk-Adjusted Valuation for Real Option Decisions
We propose a risk-adjusted valuation model to facilitate investors' subjective decision making, in response to the market valuation of an investment opportunity.
Differential Privacy in Personalized Pricing with Nonparametric Demand Models
In the recent decades, the advance of information technology and abundant personal data facilitate the application of algorithmic personalized pricing.
X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning
X-GOAL is comprised of two components: the GOAL framework, which learns node embeddings for each homogeneous graph layer, and an alignment regularization, which jointly models different layers by aligning layer-specific node embeddings.
Predicting isocitrate dehydrogenase mutation status in glioma using structural brain networks and graph neural networks
Here we propose a method to predict IDH mutation using GNN, based on the structural brain network of patients.
Adaptive unsupervised learning with enhanced feature representation for intra-tumor partitioning and survival prediction for glioblastoma
In this paper, we propose an adaptive unsupervised learning approach for efficient MRI intra-tumor partitioning and glioblastoma survival prediction.
CONNER: A Cascade Count and Measurement Extraction Tool for Scientific Discourse
Accordingly, we propose CONNER, a cascade count and measurement extraction tool that can identify entities and the corresponding relations in a two-step pipeline model.
Pruning Ternary Quantization
To simultaneously optimize bit-width, model size, and accuracy, we propose pruning ternary quantization (PTQ): a simple, effective, symmetric ternary quantization method.
Adversarial Robustness of Probabilistic Network Embedding for Link Prediction
However, these methods lack transparency when compared to simpler baselines, and as a result their robustness against adversarial attacks is a possible point of concern: could one or a few small adversarial modifications to the network have a large impact on the link prediction performance when using a network embedding model?
PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction
Joint extraction of entities and relations from unstructured texts is a crucial task in information extraction.
PRASEMap: A Probabilistic Reasoning and Semantic Embedding based Knowledge Graph Alignment System
Knowledge Graph (KG) alignment aims at finding equivalent entities and relations (i. e., mappings) between two KGs.
Field Embedding: A Unified Grain-Based Framework for Word Representation
Word representations empowered with additional linguistic information have been widely studied and proved to outperform traditional embeddings.
Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning
Despite recent advances in its theoretical understanding, there still remains a significant gap in the ability of existing PAC-Bayesian theories on meta-learning to explain performance improvements in the few-shot learning setting, where the number of training examples in the target tasks is severely limited.
OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding
Semantic embedding has been widely investigated for aligning knowledge graph (KG) entities.
Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding
Knowledge Graph (KG) alignment is to discover the mappings (i. e., equivalent entities, relations, and others) between two KGs.
Accent Recognition with Hybrid Phonetic Features
The performance of voice-controlled systems is usually influenced by accented speech.
Interventional Aspect-Based Sentiment Analysis
Recent neural-based aspect-based sentiment analysis approaches, though achieving promising improvement on benchmark datasets, have reported suffering from poor robustness when encountering confounder such as non-target aspects.
Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management
For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL. To solve this problem, many strategies have been proposed to give proper rewards when training RL, but their rewards lack interpretability and cannot accurately estimate the distribution of state-action pairs in real dialogs.
FEW-SHOTLEARNING WITH WEAK SUPERVISION
Few-shot meta-learning methods aim to learn the common structure shared across a set of tasks to facilitate learning new tasks with small amounts of data.
BrainNetGAN: Data augmentation of brain connectivity using generative adversarial network for dementia classification
The proposed BrainNetGAN is a generative adversarial network variant to augment the brain structural connectivity matrices for binary dementia classification tasks.
No Weighted-Regret Learning in Adversarial Bandits with Delays
Using these bounds, we show that FKM and EXP3 have no weighted-regret even for $d_{t}=O\left(t\log t\right)$.
Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms
Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem.
Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference
Based on the proposed VRMOM estimator, we develop a general distributed inference algorithm that is robust against Byzantine failures.
Lifelong Learning based Disease Diagnosis on Clinical Notes
Current deep learning based disease diagnosis systems usually fall short in catastrophic forgetting, i. e., directly fine-tuning the disease diagnosis model on new tasks usually leads to abrupt decay of performance on previous tasks.
Learning a Product Relevance Model from Click-Through Data in E-Commerce
We propose a novel way to consider samples of different relevance confidence, and come up with a new training objective to learn a robust relevance model with desirable score distribution.
Does Probabilistic Constellation Shaping Benefit IM-DD Systems without Optical Amplifiers?
Probabilistic constellation shaping (PCS) has been widely applied to amplified coherent optical transmissions owing to its shaping gain over the uniform signaling and fine-grained rate adaptation to the underlying fiber channel condition.
Online Statistical Inference for Stochastic Optimization via Kiefer-Wolfowitz Methods
We first present the asymptotic distribution for the Polyak-Ruppert-averaging type Kiefer-Wolfowitz (AKW) estimators, whose asymptotic covariance matrices depend on the distribution of search directions and the function-value query complexity.
Monitoring SEIRD model parameters using MEWMA for the COVID-19 pandemic with application to the State of Qatar
During the current COVID-19 pandemic, decision makers are tasked with implementing and evaluating strategies for both treatment and disease prevention.
Methodology Applications
Experimental implementation of precisely tailored light-matter interaction via inverse engineering
Here, we implement fast and robust control for the state preparation and state engineering in a rare-earth ions system.
Quantum Physics
Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion
Taxonomy is a hierarchically structured knowledge graph that plays a crucial role in machine intelligence.
Magnetic Resonance Spectroscopy Deep Learning Denoising Using Few In Vivo Data
A deep learning model, Refusion Long Short-Term Memory (ReLSTM), was designed to learn the mapping from the low SNR time-domain data (24 SA) to the high SNR one (128 SA).
Expectation-Maximization Regularized Deep Learning for Weakly Supervised Tumor Segmentation for Glioblastoma
EMReDL showed to effectively segment the infiltrated tumor from the partially labelled region of potential infiltration.
Adversarial Combinatorial Bandits with General Non-linear Reward Functions
{The adversarial combinatorial bandit with general non-linear reward is an important open problem in bandit literature, and it is still unclear whether there is a significant gap from the case of linear reward, stochastic bandit, or semi-bandit feedback.}
KETG: A Knowledge Enhanced Text Generation Framework
Embedding logical knowledge information into text generation is a challenging NLP task.
Conditional Diffusion for Interactive Segmentation
In click-based interactive segmentation, the mask extraction process is dictated by positive/negative user clicks; however, most existing methods do not fully exploit the user cues, requiring excessive numbers of clicks for satisfactory results.
Smoothed Gaussian Mixture Models for Video Classification and Recommendation
SGMM represents each video by the parameters of a Gaussian mixture model (GMM) trained for that video.
Full C-Band WDM Transmission of Nonlinearity-Tolerant Probabilistically Shaped QAM over 2824-km Dispersion-Managed Fiber
By tailoring probabilistic constellation shaping (PCS) for nonlinearity tolerance, we experimentally demonstrate up to 1. 1 dB increase in signal-to-noise ratio (SNR) and 6. 4% increase in total net data rate (NDR) compared to linear-channel-optimized PCS on a 2824-km dispersion-managed wavelength-division multiplexed (WDM) optical fiber link.
Bayesian optimization assisted unsupervised learning for efficient intra-tumor partitioning in MRI and survival prediction for glioblastoma patients
Although successful in tumor sub-region segmentation and survival prediction, radiomics based on machine learning algorithms, is challenged by its robustness, due to the vague intermediate process and track changes.
Distant Supervision for E-commerce Query Segmentation via Attention Network
The booming online e-commerce platforms demand highly accurate approaches to segment queries that carry the product requirements of consumers.
Enhanced Few-shot Learning for Intrusion Detection in Railway Video Surveillance
Video surveillance is gaining increasing popularity to assist in railway intrusion detection in recent years.
Summarizing Chinese Medical Answer with Graph Convolution Networks and Question-focused Dual Attention
It is desirable to generate answer summaries for online search engines, particularly summaries that can reveal direct answers to questions.
An Industry Evaluation of Embedding-based Entity Alignment
Embedding-based entity alignment has been widely investigated in recent years, but most proposed methods still rely on an ideal supervised learning setting with a large number of unbiased seed mappings for training and validation, which significantly limits their usage.
Binary Choice with Asymmetric Loss in a Data-Rich Environment: Theory and an Application to Racial Justice
We study the binary choice problem in a data-rich environment with asymmetric loss functions.
Improving Text Generation Evaluation with Batch Centering and Tempered Word Mover Distance
Recent advances in automatic evaluation metrics for text have shown that deep contextualized word representations, such as those generated by BERT encoders, are helpful for designing metrics that correlate well with human judgements.
DoubleEnsemble: A New Ensemble Method Based on Sample Reweighting and Feature Selection for Financial Data Analysis
Modern machine learning models (such as deep neural networks and boosting decision tree models) have become increasingly popular in financial market prediction, due to their superior capacity to extract complex non-linear patterns.
Privacy-Preserving Dynamic Personalized Pricing with Demand Learning
In this paper, we consider a dynamic pricing problem over $T$ time periods with an \emph{unknown} demand function of posted price and personalized information.
Experimental Demonstration of 4,294,967,296-QAM Based Y-00 Quantum Stream Cipher Carrying 160-Gb/s 16-QAM Signals
We demonstrate a 4, 294, 967, 296-ary quadrature amplitude modulation (QAM) based Y-00 quantum stream cipher system carrying 160-Gb/s 16-QAM signal transmitted over 320-km SSMF.
Designing Compact Features for Remote Stroke Rehabilitation Monitoring using Wearable Accelerometers
Stroke is known as a major global health problem, and for stroke survivors it is key to monitor the recovery levels.
Finding Influential Instances for Distantly Supervised Relation Extraction
Distant supervision (DS) is a strong way to expand the datasets for enhancing relation extraction (RE) models but often suffers from high label noise.
Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks
We propose a Healthcare Graph Convolutional Network (HealGCN) to offer disease self-diagnosis service for online users based on Electronic Healthcare Records (EHRs).
Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
Counterfactual learning for dealing with missing-not-at-random data (MNAR) is an intriguing topic in the recommendation literature since MNAR data are ubiquitous in modern recommender systems.
On the Sample Complexity of Reinforcement Learning with Policy Space Generalization
To avoid such undesirable dependence on the state and action space sizes, this paper proposes a new notion of eluder dimension for the policy space, which characterizes the intrinsic complexity of policy learning in an arbitrary Markov Decision Process (MDP).
Transformer with Bidirectional Decoder for Speech Recognition
To demonstrate our proposed speech transformer with a bidirectional decoder(STBD), we conduct extensive experiments on the AISHELL-1 dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Variable Skipping for Autoregressive Range Density Estimation
In this paper, we explore a technique, variable skipping, for accelerating range density estimation over deep autoregressive models.
Curves of maximal moduli on K3 surfaces
We prove that if $X$ is a complex projective K3 surface and $g>0$, then there exist infinitely many families of curves of geometric genus $g$ on $X$ with maximal, i. e., $g$-dimensional, variation in moduli.
Algebraic Geometry 14J28, 14N35, 14G17
Human-centered collaborative robots with deep reinforcement learning
We present a reinforcement learning based framework for human-centered collaborative systems.
NeuroCard: One Cardinality Estimator for All Tables
Query optimizers rely on accurate cardinality estimates to produce good execution plans.
COVID-19 Public Opinion and Emotion Monitoring System Based on Time Series Thermal New Word Mining
With the spread and development of new epidemics, it is of great reference value to identify the changing trends of epidemics in public emotions.
Non-iterative Simultaneous Rigid Registration Method for Serial Sections of Biological Tissue
In this paper, we propose a novel non-iterative algorithm to simultaneously estimate optimal rigid transformation for serial section images, which is a key component in volume reconstruction of serial sections of biological tissue.
Learning and Testing Junta Distributions with Subcube Conditioning
The main contribution is an algorithm for finding relevant coordinates in a $k$-junta distribution with subcube conditioning [BC18, CCKLW20].
DAN: A Deformation-Aware Network for Consecutive Biomedical Image Interpolation
The continuity of biological tissue between consecutive biomedical images makes it possible for the video interpolation algorithm, to recover large area defects and tears that are common in biomedical images.
Investigation of Singing Voice Separation for Singing Voice Detection in Polyphonic Music
Singing voice detection (SVD), to recognize vocal parts in the song, is an essential task in music information retrieval (MIR).
Distributed Estimation for Principal Component Analysis: an Enlarged Eigenspace Analysis
To abandon this eigengap assumption, we consider a new route in our analysis: instead of exactly identifying the top-$L$-dim eigenspace, we show that our estimator is able to cover the targeted top-$L$-dim population eigenspace.
Dimension Independent Generalization Error by Stochastic Gradient Descent
One classical canon of statistics is that large models are prone to overfitting, and model selection procedures are necessary for high dimensional data.
Resolution Adaptive Networks for Efficient Inference
Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks.
Uncertainty Quantification for Demand Prediction in Contextual Dynamic Pricing
In this paper, using the problem of demand function prediction in dynamic pricing as the motivating example, we study the problem of constructing accurate confidence intervals for the demand function.
State-Aware Tracker for Real-Time Video Object Segmentation
For higher efficiency, SAT takes advantage of the inter-frame consistency and deals with each target object as a tracklet.
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm
We study the fixed-support Wasserstein barycenter problem (FS-WBP), which consists in computing the Wasserstein barycenter of $m$ discrete probability measures supported on a finite metric space of size $n$.
Online Covariance Matrix Estimation in Stochastic Gradient Descent
This approach fits in an online setting and takes full advantage of SGD: efficiency in computation and memory.
ALPINE: Active Link Prediction using Network Embedding
Often, the link status of a node pair can be queried, which can be used as additional information by the link prediction algorithm.
On the Fairness of Randomized Trials for Recommendation with Heterogeneous Demographics and Beyond
Observed events in recommendation are consequence of the decisions made by a policy, thus they are usually selectively labeled, namely the data are Missing Not At Random (MNAR), which often causes large bias to the estimate of true outcomes risk.
Correcting Knowledge Base Assertions
The usefulness and usability of knowledge bases (KBs) is often limited by quality issues.
Adaptive Discrete Smoothing for High-Dimensional and Nonlinear Panel Data
In this paper we develop a data-driven smoothing technique for high-dimensional and non-linear panel data models.
BIG-bench Machine Learning
Vocal Bursts Intensity Prediction
EdgeDRNN: Enabling Low-latency Recurrent Neural Network Edge Inference
This paper presents a Gated Recurrent Unit (GRU) based recurrent neural network (RNN) accelerator called EdgeDRNN designed for portable edge computing.
Small-footprint Keyword Spotting with Graph Convolutional Network
Despite the recent successes of deep neural networks, it remains challenging to achieve high precision keyword spotting task (KWS) on resource-constrained devices.
Online EXP3 Learning in Adversarial Bandits with Delayed Feedback
An adversary chooses the cost of each arm in a bounded interval, and a sequence of feedback delays \left\{ d_{t}\right\} that are unknown to the player.
Random Restrictions of High-Dimensional Distributions and Uniformity Testing with Subcube Conditioning
We give a nearly-optimal algorithm for testing uniformity of distributions supported on $\{-1, 1\}^n$, which makes $\tilde O (\sqrt{n}/\varepsilon^2)$ queries to a subcube conditional sampling oracle (Bhattacharyya and Chakraborty (2018)).
Solving Optimization Problems through Fully Convolutional Networks: an Application to the Travelling Salesman Problem
Based on samples of a 10 city TSP, a fully convolutional network (FCN) is used to learn the mapping from a feasible region to an optimal solution.
Thresholding Bandit Problem with Both Duels and Pulls
The Thresholding Bandit Problem (TBP) aims to find the set of arms with mean rewards greater than a given threshold.
Robust Dynamic Assortment Optimization in the Presence of Outlier Customers
We establish both upper and lower bounds on the regret, and show that our policy is optimal up to logarithmic factor in $T$ when the assortment capacity is constant.
Skew-Explore: Learn faster in continuous spaces with sparse rewards
In this work, we introduce an exploration approach based on maximizing the entropy of the visited states while learning a goal-conditioned policy.
Learning Visual Relation Priors for Image-Text Matching and Image Captioning with Neural Scene Graph Generators
In this work, we tackle two fundamental language-and-vision tasks: image-text matching and image captioning, and demonstrate that neural scene graph generators can learn effective visual relation features to facilitate grounding language to visual relations and subsequently improve the two end applications.
Adversarial Feature Training for Generalizable Robotic Visuomotor Control
Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs.
UER: An Open-Source Toolkit for Pre-training Models
Existing works, including ELMO and BERT, have revealed the importance of pre-training for NLP tasks.
Bayesian posterior repartitioning for nested sampling
We show through numerical examples that this Bayesian PR (BPR) method provides a very robust, self-adapting and computationally efficient `hands-off' solution to the problem of unrepresentative priors in Bayesian inference using NS.
Autoregressive-Model-Based Methods for Online Time Series Prediction with Missing Values: an Experimental Evaluation
In this paper, we focus on online methods for AR-model-based time series prediction with missing values.
Efficient average-case population recovery in the presence of insertions and deletions
In this problem, there is an unknown distribution $\cal{D}$ over $s$ unknown source strings $x^1,\dots, x^s \in \{0, 1\}^n$, and each sample is independently generated by drawing some $x^i$ from $\cal{D}$ and returning an independent trace of $x^i$.
Evaluating Protein Transfer Learning with TAPE
Semi-supervised learning has emerged as an important paradigm in protein modeling due to the high cost of acquiring supervised protein labels, but the current literature is fragmented when it comes to datasets and standardized evaluation techniques.
Distributed High-dimensional Regression Under a Quantile Loss Function
This paper studies distributed estimation and support recovery for high-dimensional linear regression model with heavy-tailed noise.