Search Results for author:
Found 424 papers, 119 papers with code
Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech
In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech.
Sound Audio and Speech Processing
LightGBM: A Highly Efficient Gradient Boosting Decision Tree
We prove that, since the data instances with larger gradients play a more important role in the computation of information gain, GOSS can obtain quite accurate estimation of the information gain with a much smaller data size.
Gradient Information Matters in Policy Optimization by Back-propagating through Model
Then we proposed a two-model-based learning method to control the prediction error and the gradient error.
Learning for Disparity Estimation through Feature Constancy
The second part performs matching cost calculation, matching cost aggregation and disparity calculation to estimate the initial disparity using shared features.
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density.
Causal-learn: Causal Discovery in Python
Causal discovery aims at revealing causal relations from observational data, which is a fundamental task in science and engineering.
R-Drop: Regularized Dropout for Neural Networks
Dropout is a powerful and widely used technique to regularize the training of deep neural networks.
Ranked #4 on
Machine Translation
on WMT2014 English-French
Position Paper: What Can Large Language Models Tell Us about Time Series Analysis
Time series analysis is essential for comprehending the complexities inherent in various real-world systems and applications.
DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services
We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services.
DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning
We propose Multiple Experts Fine-tuning Framework to build a financial large language model (LLM), DISC-FinLLM.
DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation
We propose DISC-MedLLM, a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services.
Large Language Models for Generative Information Extraction: A Survey
Information extraction (IE) aims to extract structural knowledge (such as entities, relations, and events) from plain natural language texts.
CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention
On the one hand, CEL blends each token with multiple patches of different scales, providing the self-attention module itself with cross-scale features.
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
If the initial image is not well initialized, the following processes can hardly refine the image to a satisfactory quality.
Ranked #6 on
Text-to-Image Generation
on CUB
(Inception score metric)
Dual Supervised Learning
Many supervised learning tasks are emerged in dual forms, e. g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation.
Learning to Predict the Cosmological Structure Formation
We build a deep neural network, the Deep Density Displacement Model (hereafter D$^3$M), to predict the non-linear structure formation of the Universe from simple linear perturbation theory.
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
During training, both the dynamic discriminator and the static BLEU objective are employed to evaluate the generated sentences and feedback the evaluations to guide the learning of the generator.
G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
Third, via the predicted segmentation and translation, we transfer the fine object point cloud into a local canonical coordinate, in which we train a rotation localization network to estimate initial object rotation.
KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
(2) A dynamic weighting strategy named Consensus Focus to identify both the malicious and irrelevant domains.
Knowledge Distillation
Multi-Source Unsupervised Domain Adaptation
+2
Unsupervised Neural Machine Translation with Weight Sharing
Unsupervised neural machine translation (NMT) is a recently proposed approach for machine translation which aims to train the model without using any labeled data.
Ranked #6 on
Machine Translation
on WMT2016 German-English
FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism
In this paper, we focus on category-level 6D pose and size estimation from monocular RGB-D image.
Ranked #7 on
6D Pose Estimation using RGBD
on REAL275
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
The privacy leakage of the model about the training data can be bounded in the differential privacy mechanism.
Large Scale Private Learning via Low-rank Reparametrization
We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffering notorious dimensional dependence.
Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
In this work we explore a new and challenging ReID task, namely lifelong person re-identification (LReID), which enables to learn continuously across multiple domains and even generalise on new and unseen domains.
Towards Binary-Valued Gates for Robust LSTM Training
Long Short-Term Memory (LSTM) is one of the most widely used recurrent structures in sequence modeling.
Learning Causal Semantic Representation for Out-of-Distribution Prediction
Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output.
MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding
Reading comprehension of legal text can be a particularly challenging task due to the length and complexity of legal clauses and a shortage of expert-annotated datasets.
Deep Learning for Trajectory Data Management and Mining: A Survey and Beyond
In this paper, we present a comprehensive review of the development and recent advances in deep learning for trajectory computing (DL4Traj).
Hierarchical Reinforcement Learning for Automatic Disease Diagnosis
Existing approaches usually employ a flat policy structure that treat all symptoms and diseases equally for action making.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets
In recent years, interest has arisen in using machine learning to improve the efficiency of automatic medical consultation and enhance patient experience.
Feature-Proxy Transformer for Few-Shot Segmentation
With a rethink of recent advances, we find that the current FSS framework has deviated far from the supervised segmentation framework: Given the deep features, FSS methods typically use an intricate decoder to perform sophisticated pixel-wise matching, while the supervised segmentation methods use a simple linear classification head.
CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation
However, existing methods for empathetic response generation usually either consider only one empathy factor or ignore the hierarchical relationships between different factors, leading to a weak ability of empathy modeling.
Hyper-3DG: Text-to-3D Gaussian Generation via Hypergraph
Our framework is anchored by a well-established mainflow and an essential module, named ``Geometry and Texture Hypergraph Refiner (HGRefiner)''.
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation
Dialog response generation in open domain is an important research topic where the main challenge is to generate relevant and diverse responses.
Airfoil Design Parameterization and Optimization using Bézier Generative Adversarial Networks
The resulted new parameterization can accelerate design optimization convergence by improving the representation compactness while maintaining sufficient representation capacity.
Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning
The surge in Large Language Models (LLMs) has revolutionized natural language processing, but fine-tuning them for specific tasks often encounters challenges in balancing performance and preserving general instruction-following abilities.
SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations
Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference results.
SupportNet: solving catastrophic forgetting in class incremental learning with support data
A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting.
CoSDA: Continual Source-Free Domain Adaptation
Recently, SFDA has gained popularity due to the need to protect the data privacy of the source domain, but it suffers from catastrophic forgetting on the source domain due to the lack of data.
MetaSleepLearner: A Pilot Study on Fast Adaptation of Bio-signals-Based Sleep Stage Classifier to New Individual Subject Using Meta-Learning
This is the first work that investigated a non-conventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification and easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.
Fourier-Net: Fast Image Registration with Band-limited Deformation
Specifically, instead of our Fourier-Net learning to output a full-resolution displacement field in the spatial domain, we learn its low-dimensional representation in a band-limited Fourier domain.
Ranked #3 on
Medical Image Registration
on OASIS
(val dsc metric)
PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation
Generative text-to-image models have gained great popularity among the public for their powerful capability to generate high-quality images based on natural language prompts.
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data.
Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart
Along with this routine, we find that confidence and a rectified confidence (R-Con) can form two coupled rejection metrics, which could provably distinguish wrongly classified inputs from correctly classified ones.
Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives
Foundation models have indeed made a profound impact on various fields, emerging as pivotal components that significantly shape the capabilities of intelligent systems.
Factorization Bandits for Online Influence Maximization
We capitalize on an important property of the influence maximization problem named network assortativity, which is ignored by most existing works in online influence maximization.
Enhanced Hyperspectral Image Super-Resolution via RGB Fusion and TV-TV Minimization
Such methods, however, cannot guarantee that the input measurements are satisfied in the recovered image, since the learned parameters by the network are applied to every test image.
PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design
Engineering design tasks often require synthesizing new designs that meet desired performance requirements.
Recovering Latent Causal Factor for Generalization to Distributional Shifts
To avoid such a spurious correlation, we propose \textbf{La}tent \textbf{C}ausal \textbf{I}nvariance \textbf{M}odels (LaCIM) that specifies the underlying causal structure of the data and the source of distributional shifts, guiding us to pursue only causal factor for prediction.
Does Federated Learning Really Need Backpropagation?
BAFFLE is 1) memory-efficient and easily fits uploading bandwidth; 2) compatible with inference-only hardware optimization and model quantization or pruning; and 3) well-suited to trusted execution environments, because the clients in BAFFLE only execute forward propagation and return a set of scalars to the server.
Lero: A Learning-to-Rank Query Optimizer
In this paper, we introduce a learning-to-rank query optimizer, called Lero, which builds on top of a native query optimizer and continuously learns to improve the optimization performance.
The NPU-ASLP-LiAuto System Description for Visual Speech Recognition in CNVSRC 2023
This paper delineates the visual speech recognition (VSR) system introduced by the NPU-ASLP-LiAuto (Team 237) in the first Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023, engaging in the fixed and open tracks of Single-Speaker VSR Task, and the open track of Multi-Speaker VSR Task.
Graph Diffusion Policy Optimization
Recent research has made significant progress in optimizing diffusion models for specific downstream objectives, which is an important pursuit in fields such as graph generation for drug design.
SE(3) Equivariant Graph Neural Networks with Complete Local Frames
In this paper, we propose a framework to construct SE(3) equivariant graph neural networks that can approximate the geometric quantities efficiently.
FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning
In this paper, we identify a new phenomenon called activation-divergence which occurs in Federated Learning (FL) due to data heterogeneity (i. e., data being non-IID) across multiple users.
On the Exploration of Incremental Learning for Fine-grained Image Retrieval
On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting.
Continual Learning with Filter Atom Swapping
In this paper, we first enforce a low-rank filter subspace by decomposing convolutional filters within each network layer over a small set of filter atoms.
Vector and Line Quantization for Billion-scale Similarity Search on GPUs
The inverted index structure is amenable to GPU-based implementations, and the state-of-the-art systems such as Faiss are able to exploit the massive parallelism offered by GPUs.
PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse Designs
With this new loss function, we develop a variant of the Generative Adversarial Network, named "Performance Augmented Diverse Generative Adversarial Network" or PaDGAN, which can generate novel high-quality designs with good coverage of the design space.
Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction
A more challenging scenario is that emerging KGs consist of only unseen entities, called as disconnected emerging KGs (DEKGs).
Reinforcement Learning with Dynamic Boltzmann Softmax Updates
In this paper, we propose to update the value function with dynamic Boltzmann softmax (DBS) operator, which has good convergence property in the setting of planning and learning.
DxFormer: A Decoupled Automatic Diagnostic System Based on Decoder-Encoder Transformer with Dense Symptom Representations
Diagnosis-oriented dialogue system queries the patient's health condition and makes predictions about possible diseases through continuous interaction with the patient.
METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design
In answer, we posit that a smaller yet diverse set of unit cells leads to scalable search and unbiased learning.
Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations
We study the problem of coarse-grained response selection in retrieval-based dialogue systems.
D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights
We present a trajectory prediction approach with respect to traffic lights, D2-TPred, which uses a spatial dynamic interaction graph (SDG) and a behavior dependency graph (BDG) to handle the problem of discontinuous dependency in the spatial-temporal space.
AI Hospital: Interactive Evaluation and Collaboration of LLMs as Intern Doctors for Clinical Diagnosis
To simulate the procedure, we collect high-quality medical records to create patient, examiner, and medical director agents.
decoupleQ: Towards 2-bit Post-Training Uniform Quantization via decoupling Parameters into Integer and Floating Points
However, existing quantization schemes suffer from significant accuracy degradation at very low bits, or require some additional computational overhead when deployed, making it difficult to be applied to large-scale applications in industry.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Towards Enhancing Relational Rules for Knowledge Graph Link Prediction
To address these issues, we propose a novel knowledge graph reasoning approach, the Relational rUle eNhanced Graph Neural Network (RUN-GNN).
MO-PaDGAN: Reparameterizing Engineering Designs for Augmented Multi-objective Optimization
Despite their success in capturing complex distributions, existing generative models face three challenges when used for design problems: 1) generated designs have limited design space coverage, 2) the generator ignores design performance, and 3)~the new parameterization is unable to represent designs beyond training data.
A Plug-and-Play Priors Framework for Hyperspectral Unmixing
Spectral unmixing is a widely used technique in hyperspectral image processing and analysis.
Prior-Enhanced Few-Shot Segmentation with Meta-Prototypes
The hierarchical features help the model highlight the decision boundary and focus on hard pixels, and the structural information learned from base classes is treated as the prior knowledge for novel classes.
Mutual Distillation Learning Network for Trajectory-User Linking
In this paper, we propose a novel Mutual distillation learning network to solve the TUL problem for sparse check-in mobility data, named MainTUL.
How Does Data Augmentation Affect Privacy in Machine Learning?
Even further, we show that the proposed approach can achieve higher MI attack success rates on models trained with some data augmentation than the existing methods on models trained without data augmentation.
Range-GAN: Range-Constrained Generative Adversarial Network for Conditioned Design Synthesis
This work laid the foundation for data-driven inverse design problems where we consider range constraints and there are sparse regions in the condition space.
EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning
Generating informative and appropriate responses is challenging but important for building human-like dialogue systems.
Multi-Round Influence Maximization (Extended Version)
In this paper, we study the Multi-Round Influence Maximization (MRIM) problem, where influence propagates in multiple rounds independently from possibly different seed sets, and the goal is to select seeds for each round to maximize the expected number of nodes that are activated in at least one round.
Social and Information Networks
Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
To solve the problem, we present a carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively.
Availability Attacks Create Shortcuts
We are the first to unveil an important population property of the perturbations of these attacks: they are almost \textbf{linearly separable} when assigned with the target labels of the corresponding samples, which hence can work as \emph{shortcuts} for the learning objective.
A Knowledge-based Learning Framework for Self-supervised Pre-training Towards Enhanced Recognition of Biomedical Microscopy Images
Self-supervised pre-training has become the priory choice to establish reliable neural networks for automated recognition of massive biomedical microscopy images, which are routinely annotation-free, without semantics, and without guarantee of quality.
Enlighten-Your-Voice: When Multimodal Meets Zero-shot Low-light Image Enhancement
Low-light image enhancement is a crucial visual task, and many unsupervised methods tend to overlook the degradation of visible information in low-light scenes, which adversely affects the fusion of complementary information and hinders the generation of satisfactory results.
HEProto: A Hierarchical Enhancing ProtoNet based on Multi-Task Learning for Few-shot Named Entity Recognition
Great efforts have been made on this task with competitive performance, however, they usually treat the two subtasks, namely span detection and type classification, as mutually independent, and the integrity and correlation between subtasks have been largely ignored.
Ranked #3 on
Few-shot NER
on Few-NERD (INTER)
Efficient Approximation Algorithms for Adaptive Influence Maximization
In this paper, we propose the first practical algorithm for the adaptive IM problem that could provide the worst-case approximation guarantee of $1-\mathrm{e}^{\rho_b(\varepsilon-1)}$, where $\rho_b=1-(1-1/b)^b$ and $\varepsilon \in (0, 1)$ is a user-specified parameter.
Social and Information Networks
FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation
Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world scenarios.
REST: Debiased Social Recommendation via Reconstructing Exposure Strategies
By explicitly Reconstructing Exposure STrategies (REST in short), we formalize the recommendation problem as the counterfactual reasoning and propose the debiased social recommendation method.
Neural Operator with Regularity Structure for Modeling Dynamics Driven by SPDEs
Stochastic partial differential equations (SPDEs) are significant tools for modeling dynamics in many areas including atmospheric sciences and physics.
A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis
Recently, some span-based methods have achieved encouraging performances for joint aspect-sentiment analysis, which first extract aspects (aspect extraction) by detecting aspect boundaries and then classify the span-level sentiments (sentiment classification).
Deep Plug-and-Play Prior for Multitask Channel Reconstruction in Massive MIMO Systems
The proposed method corresponding to these three channel reconstruction tasks employs a common DL model, which greatly reduces the overhead of model training and storage.
Active Expansion Sampling for Learning Feasible Domains in an Unbounded Input Space
We evaluate AES on three test examples and compare AES with two adaptive sampling methods -- the Neighborhood-Voronoi algorithm and the straddle heuristic -- that operate over fixed input variable bounds.
Stabilize Deep ResNet with A Sharp Scaling Factor $τ$
Moreover, for ResNets with normalization layer, adding such a factor $\tau$ also stabilizes the training and obtains significant performance gain for deep ResNet.
Remixing Functionally Graded Structures: Data-Driven Topology Optimization with Multiclass Shape Blending
We propose to inherit the advantages of both through a data-driven framework for multiclass functionally graded structures that mixes several families, i. e., classes, of microstructure topologies to create spatially-varying designs with guaranteed feasibility.
TO-FLOW: Efficient Continuous Normalizing Flows with Temporal Optimization adjoint with Moving Speed
In this paper, a temporal optimization is proposed by optimizing the evolutionary time for forward propagation of the neural ODE training.
Combinatorial Causal Bandits
For the special case of linear models with hidden variables, we apply causal inference techniques such as the do-calculus to convert the original model into a Markovian model, and then show that our BGLM-OFU algorithm and another algorithm based on the linear regression both solve such linear models with hidden variables.
Rapid Design of Top-Performing Metal-Organic Frameworks with Qualitative Representations of Building Blocks
Our approach provides three main advantages: (i) no specific physical descriptors are required and only building blocks that construct the MOFs are used in global optimization through qualitative representations, (ii) the method is application and property independent, and (iii) the latent variable approach provides an interpretable model of qualitative building blocks with physical justification.
Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks
Trajectory-User Linking (TUL) is crucial for human mobility modeling by linking diferent trajectories to users with the exploration of complex mobility patterns.
Topic-oriented Adversarial Attacks against Black-box Neural Ranking Models
In this paper, we focus on a more general type of perturbation and introduce the topic-oriented adversarial ranking attack task against NRMs, which aims to find an imperceptible perturbation that can promote a target document in ranking for a group of queries with the same topic.
MolSets: Molecular Graph Deep Sets Learning for Mixture Property Modeling
This complexity is particularly evident in molecular mixtures, a frequently explored space for materials such as battery electrolytes.
CCSL: A Causal Structure Learning Method from Multiple Unknown Environments
This method simultaneously integrates the following two tasks: 1) clustering samples of the subjects with the same causal mechanism into different groups; 2) learning causal structures from the samples within the group.
Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models
A ranking model is said to be Certified Top-$K$ Robust on a ranked list when it is guaranteed to keep documents that are out of the top $K$ away from the top $K$ under any attack.
A Structure-Aware Argument Encoder for Literature Discourse Analysis
Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context.
ET-AL: Entropy-Targeted Active Learning for Bias Mitigation in Materials Data
To mitigate the bias, we develop an entropy-targeted active learning (ET-AL) framework, which guides the acquisition of new data to improve the diversity of underrepresented crystal systems.
tdCoxSNN: Time-Dependent Cox Survival Neural Network for Continuous-time Dynamic Prediction
In pursuit of constructing a dynamic prediction model for a progressive eye disorder, age-related macular degeneration (AMD), we propose a time-dependent Cox survival neural network (tdCoxSNN) to predict its progression using longitudinal fundus images.
Attention-Based CNN-BiLSTM for Sleep State Classification of Spatiotemporal Wide-Field Calcium Imaging Data
Comparison with Existing Method: On a 3-hour WFCI recording, the CNN-BiLSTM achieved a kappa of 0. 67, comparable to a kappa of 0. 65 corresponding to the human EEG/EMG-based scoring.
A Latent Variable Approach to Gaussian Process Modeling with Qualitative and Quantitative Factors
Computer simulations often involve both qualitative and numerical inputs.
DINs: Deep Interactive Networks for Neurofibroma Segmentation in Neurofibromatosis Type 1 on Whole-Body MRI
In this study, we propose deep interactive networks (DINs) to address the above limitations.
Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network
Specifically, we first structure the sequence of EMR into a hierarchical graph network and then obtain the causal relationship between multi-granularity features and diagnosis results through counterfactual intervention on the graph.
GAN-DUF: Hierarchical Deep Generative Models for Design Under Free-Form Geometric Uncertainty
To address this issue, we propose a Generative Adversarial Network-based Design under Uncertainty Framework (GAN-DUF), which contains a deep generative model that simultaneously learns a compact representation of nominal (ideal) designs and the conditional distribution of fabricated designs given any nominal design.
Deep Generative Models for Geometric Design Under Uncertainty
Deep generative models have demonstrated effectiveness in learning compact and expressive design representations that significantly improve geometric design optimization.
Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret
We propose a new learning framework that captures the tiered structure of many real-world user-interaction applications, where the users can be divided into two groups based on their different tolerance on exploration risks and should be treated separately.
Beyond Semantics: Learning a Behavior Augmented Relevance Model with Self-supervised Learning
Drawing inspiration from this, we devise a novel Behavior Augmented Relevance Learning model for Alipay Search (BARL-ASe) that leverages neighbor queries of target item and neighbor items of target query to complement target query-item semantic matching.
L^2R: Lifelong Learning for First-stage Retrieval with Backward-Compatible Representations
First-stage retrieval is a critical task that aims to retrieve relevant document candidates from a large-scale collection.
Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin
End-to-end models have been showing superiority in Automatic Speech Recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Simplex Search Based Brain Storm Optimization
Through modeling human's brainstorming process, the brain storm optimization (BSO) algorithm has become a promising population-based evolutionary algorithm.
$\mathcal{G}$-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
Then, a natural question is: \emph{can we construct a new vector space that is positively scale-invariant and sufficient to represent ReLU neural networks so as to better facilitate the optimization process }?
Differential Equations for Modeling Asynchronous Algorithms
Then we conduct theoretical analysis on the convergence rates of ASGD algorithm based on the continuous approximation.
Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications (Extended Version)
Each decision has a reward according to the distributions of arms.
Thompson Sampling for Combinatorial Semi-Bandits
We first analyze the standard TS algorithm for the general CMAB model when the outcome distributions of all the base arms are independent, and obtain a distribution-dependent regret bound of $O(m\log K_{\max}\log T / \Delta_{\min})$, where $m$ is the number of base arms, $K_{\max}$ is the size of the largest super arm, $T$ is the time horizon, and $\Delta_{\min}$ is the minimum gap between the expected reward of the optimal solution and any non-optimal solution.
Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation
This inconsistence of gradient magnitude across different layers renders optimization of deep neural network with a single learning rate problematic.
Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications
Finally, we provide lower bound results showing that the factor $1/p^*$ is unavoidable for general CMAB-T problems, suggesting that the TPM condition is crucial in removing this factor.
Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape exploration
Nonlinear machine learning techniques can identify such CVs but typically do not furnish an explicit relationship with the atomic coordinates necessary to perform biased sampling.
Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling
First, we give a mathematical formulation for the practical data processing procedure in distributed machine learning, which we call data partition with global/local shuffling.
Slim-DP: A Light Communication Data Parallelism for DNN
However, with the increasing size of DNN models and the large number of workers in practice, this typical data parallelism cannot achieve satisfactory training acceleration, since it usually suffers from the heavy communication cost due to transferring huge amount of information between workers and the parameter server.
Ensemble-Compression: A New Method for Parallel Training of Deep Neural Networks
In this framework, we propose to aggregate the local models by ensemble, i. e., averaging the outputs of local models instead of the parameters.
Asynchronous Stochastic Gradient Descent with Delay Compensation
We propose a novel technology to compensate this delay, so as to make the optimization behavior of ASGD closer to that of sequential SGD.
DIMM-SC: A Dirichlet mixture model for clustering droplet-based single cell transcriptomic data
More importantly, as a model-based approach, DIMM-SC is able to quantify the clustering uncertainty for each single cell, facilitating rigorous statistical inference and biological interpretations, which are typically unavailable from existing clustering methods.
Combinatorial Multi-Armed Bandit with General Reward Functions
Our framework enables a much larger class of reward functions such as the $\max()$ function and nonlinear utility functions.
A Communication-Efficient Parallel Algorithm for Decision Tree
After partitioning the training data onto a number of (e. g., $M$) machines, this algorithm performs both local voting and global voting in each iteration.
Asynchronous Stochastic Proximal Optimization Algorithms with Variance Reduction
The results verified our theoretical findings and demonstrated the practical efficiency of the asynchronous stochastic proximal algorithms with variance reduction.
Generalization Error Bounds for Optimization Algorithms via Stability
Many machine learning tasks can be formulated as Regularized Empirical Risk Minimization (R-ERM), and solved by optimization algorithms such as gradient descent (GD), stochastic gradient descent (SGD), and stochastic variance reduction (SVRG).
Robust Influence Maximization
In this paper, we address the important issue of uncertainty in the edge influence probability estimates for the well studied influence maximization problem --- the task of finding $k$ seed nodes in a social network to maximize the influence spread.
Combinatorial Multi-Armed Bandit and Its Extension to Probabilistically Triggered Arms
The objective of an online learning algorithm for CMAB is to minimize (\alpha,\beta)-approximation regret, which is the difference between the \alpha{\beta} fraction of the expected reward when always playing the optimal super arm, and the expected reward of playing super arms according to the algorithm.
Joint Sensing Matrix and Sparsifying Dictionary Optimization for Tensor Compressive Sensing
In this paper, we propose a joint optimization approach of the sensing matrix and dictionary for a TCS system.
On the Depth of Deep Neural Networks: A Theoretical View
First, we derive an upper bound for RA of DNN, and show that it increases with increasing depth.
Real-time Topic-aware Influence Maximization Using Preprocessing
In this paper, we focus on the topic-aware influence maximization task.
Compositional Structure Learning for Action Understanding
The focus of the action understanding literature has predominately been classification, how- ever, there are many applications demanding richer action understanding such as mobile robotics and video search, with solutions to classification, localization and detection.
Generalization Analysis for Game-Theoretic Machine Learning
For Internet applications like sponsored search, cautions need to be taken when using machine learning to optimize their mechanisms (e. g., auction) since self-interested agents in these applications may change their behaviors (and thus the data distribution) in response to the mechanisms.
Agent Behavior Prediction and Its Generalization Analysis
Then we prove a generalization bound for the machine learning algorithms on the behavior data generated by the new Markov chain, which depends on both the Markovian parameters and the covering number of the function class compounded by the loss function for behavior prediction and the behavior prediction model.
A Game-theoretic Machine Learning Approach for Revenue Maximization in Sponsored Search
Sponsored search is an important monetization channel for search engines, in which an auction mechanism is used to select the ads shown to users and determine the prices charged from advertisers.
Approximate dynamic programming using fluid and diffusion approximations with applications to power management
Neuro-dynamic programming is a class of powerful techniques for approximating the solution to dynamic programming equations.
A Theoretical Analysis of NDCG Type Ranking Measures
We show that NDCG with logarithmic discount has consistent distinguishability although it converges to the same limit for all ranking functions.
BézierGAN: Automatic Generation of Smooth Curves from Interpretable Low-Dimensional Parameters
Many real-world objects are designed by smooth curves, especially in the domain of aerospace and ship, where aerodynamic shapes (e. g., airfoils) and hydrodynamic shapes (e. g., hulls) are designed.
Capacity Control of ReLU Neural Networks by Basis-path Norm
Motivated by this, we propose a new norm \emph{Basis-path Norm} based on a group of linearly independent paths to measure the capacity of neural networks more accurately.
Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting
(2) The convergence rate is determined by the step size, with the mixing time of the Markov process as the coefficient.
Improving the Robustness of Speech Translation
Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech recognition (ASR) system due to the enormous errors in the source.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Modality Attention for End-to-End Audio-visual Speech Recognition
In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance.
Audio-Visual Speech Recognition
Robust Speech Recognition
+2
An Online Attention-based Model for Speech Recognition
In previous work, researchers have shown that such architectures can acquire comparable results to state-of-the-art ASR systems, especially when using a bidirectional encoder and global soft attention (GSA) mechanism.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Community Exploration: From Offline Optimization to Online Learning
We introduce the community exploration problem that has many real-world applications such as online advertising.
Exploring RNN-Transducer for Chinese Speech Recognition
End-to-end approaches have drawn much attention recently for significantly simplifying the construction of an automatic speech recognition (ASR) system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Peperomia at SemEval-2018 Task 2: Vector Similarity Based Approach for Emoji Prediction
First the distributed representation (tweet vector) for each tweet is generated, then the similarity between this tweet vector and each emoji{'}s embedding is evaluated.
Towards Compact and Fast Neural Machine Translation Using a Combined Method
Neural Machine Translation (NMT) lays intensive burden on computation and memory cost.
Semi-Supervised Disfluency Detection
While the disfluency detection has achieved notable success in the past years, it still severely suffers from the data scarcity.
A Character-Aware Encoder for Neural Machine Translation
This article proposes a novel character-aware neural machine translation (NMT) model that views the input sequences as sequences of characters rather than words.
On the Local Hessian in Back-propagation
We study the Hessian of the local back-matching loss (local Hessian) and connect it to the efficiency of BP.
Influence Maximization with \varepsilon-Almost Submodular Threshold Functions
Influence maximization is the problem of selecting $k$ nodes in a social network to maximize their influence spread.
Stochastic Online Greedy Learning with Semi-bandit Feedbacks
We further show that the bound is tight in $T$ and other problem instance parameters.
Combinatorial Pure Exploration of Multi-Armed Bandits
We also establish a general problem-dependent lower bound for the CPE problem.
Two-Layer Generalization Analysis for Ranking Using Rademacher Average
sampling of queries and the conditional i. i. d sampling of documents per query.
Ranking Measures and Loss Functions in Learning to Rank
We show that these loss functions are upper bounds of the measure-based ranking errors.
Optimization on Multiple Manifolds
Optimization on manifold has been widely used in machine learning, to handle optimization problems with constraint.
G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
Then, a natural question is: \emph{can we construct a new vector space that is positively scale-invariant and sufficient to represent ReLU neural networks so as to better facilitate the optimization process }?
Actionness Ranking with Lattice Conditional Ordinal Random Fields
Action analysis in image and video has been attracting more and more attention in computer vision.
Action Detection by Implicit Intentional Motion Clustering
This paper hence seeks to understand the spatiotemporal properties of intentional movement and how to capture such intentional movement without relying on challenging human detection and tracking.
Low-Rank Tensor Completion: A Pseudo-Bayesian Learning Approach
Low rank tensor completion, which solves a linear inverse problem with the principle of parsimony, is a powerful technique used in many application domains in computer vision and pattern recognition.
Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets
The success of enhanced sampling molecular simulations that accelerate along collective variables (CVs) is predicated on the availability of variables coincident with the slow collective motions governing the long-time conformational dynamics of a system.
Improved Algorithm on Online Clustering of Bandits
We generalize the setting of online clustering of bandits by allowing non-uniform distribution over user frequencies.
Stochastic Online Learning with Probabilistic Graph Feedback
We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability $p_{ij}$.
Positively Scale-Invariant Flatness of ReLU Neural Networks
That is to say, the minimum with balanced values of basis paths will more likely to be flatter and generalize better.
The Roadmap to 6G -- AI Empowered Wireless Networks
The recent upsurge of diversified mobile applications, especially those supported by Artificial Intelligence (AI), is spurring heated discussions on the future evolution of wireless communications.
An Interactive Insight Identification and Annotation Framework for Power Grid Pixel Maps using DenseU-Hierarchical VAE
Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid.
Convergence of Distributed Stochastic Variance Reduced Methods without Sampling Extra Data
Our theory captures how the convergence of distributed algorithms behaves as the number of machines and the size of local data vary.
Capabilities and Limitations of Time-lagged Autoencoders for Slow Mode Discovery in Dynamical Systems
We also compare the TAE results with those obtained using state-free reversible VAMPnets (SRVs) as a variational-based neural network approach for slow modes discovery, and show that SRVs can correctly discover slow modes where TAEs fail.
IMRank: Influence Maximization via Finding Self-Consistent Ranking
Early methods mainly fall into two paradigms with certain benefits and drawbacks: (1)Greedy algorithms, selecting seed nodes one by one, give a guaranteed accuracy relying on the accurate approximation of influence spread with high computational cost; (2)Heuristic algorithms, estimating influence spread using efficient heuristics, have low computational cost but unstable accuracy.
Social and Information Networks Data Structures and Algorithms F.2.2; D.2.8
Influence Diffusion Dynamics and Influence Maximization in Social Networks with Friend and Foe Relationships
Influence diffusion and influence maximization in large-scale online social networks (OSNs) have been extensively studied, because of their impacts on enabling effective online viral marketing.
Social and Information Networks Discrete Mathematics Physics and Society E.1; H.3.3
From Competition to Complementarity: Comparative Influence Diffusion and Maximization
We study two natural optimization problems, Self Influence Maximization and Complementary Influence Maximization, in a novel setting with complementary entities.
Social and Information Networks Physics and Society H.2.8
Adaptive Influence Maximization with Myopic Feedback
We study the adaptive influence maximization problem with myopic feedback under the independent cascade model: one sequentially selects k nodes as seeds one by one from a social network, and each selected seed returns the immediate neighbors it activates as the feedback available for later selections, and the goal is to maximize the expected number of total activated nodes, referred as the influence spread.
Social and Information Networks
High-resolution Markov state models for the dynamics of Trp-cage miniprotein constructed over slow folding modes identified by state-free reversible VAMPnets
State-free reversible VAMPnets (SRVs) are a neural network-based framework capable of learning the leading eigenfunctions of the transfer operator of a dynamical system from trajectory data.
Stochastic One-Sided Full-Information Bandit
In this paper, we study the stochastic version of the one-sided full information bandit problem, where we have $K$ arms $[K] = \{1, 2, \ldots, K\}$, and playing arm $i$ would gain reward from an unknown distribution for arm $i$ while obtaining reward feedback for all arms $j \ge i$.
Self-Activation Influence Maximization
We incorporate self activation into influence propagation and propose the self-activation independent cascade (SAIC) model: nodes may be self activated besides being selected as seeds, and influence propagates from both selected seeds and self activated nodes.
Social and Information Networks
Data-Centric Mixed-Variable Bayesian Optimization For Materials Design
To this end, we present a data-centric, mixed-variable Bayesian Optimization framework that integrates data from literature, experiments, and simulations for knowledge discovery and computational materials design.
A Natural-language-based Visual Query Approach of Uncertain Human Trajectories
Visual querying is essential for interactively exploring massive trajectory data.
Scalable Influence Maximization with General Marketing Strategies
In this paper, we study scalable algorithms for influence maximization with general marketing strategies (IM-GMS), in which a marketing strategy mix is modeled as a vector $\mathbf{x}=(x_1, \ldots, x_d)$ and could activate a node $v$ in the social network with probability $h_v(\mathbf{x})$.
Social and Information Networks Data Structures and Algorithms
Bayesian Optimization for Materials Design with Mixed Quantitative and Qualitative Variables
We present in this paper the integration of a novel latent-variable (LV) approach for mixed-variable GP modeling with the BO framework for materials design.
A Conditional Generative Model for Predicting Material Microstructures from Processing Methods
Microstructures of a material form the bridge linking processing conditions - which can be controlled, to the material property - which is the primary interest in engineering applications.
Interpreting Basis Path Set in Neural Networks
Based on basis path set, G-SGD algorithm significantly outperforms conventional SGD algorithm in optimizing neural networks.
Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding
Transformer has shown promising results in many sequence to sequence transformation tasks recently.
Online Second Price Auction with Semi-bandit Feedback Under the Non-Stationary Setting
The problem is more challenging than the standard online learning scenario since the private value distribution is non-stationary, meaning that the distribution of bidders' private values may change over time, and we need to use the \emph{non-stationary regret} to measure the performance of our algorithm.
Gradient Perturbation is Underrated for Differentially Private Convex Optimization
By using the \emph{expected curvature}, we show that gradient perturbation can achieve a significantly improved utility guarantee that can theoretically justify the advantage of gradient perturbation over other perturbation methods.
Adaptive Greedy versus Non-adaptive Greedy for Influence Maximization
On the other side, we prove that in any submodular cascade, the adaptive greedy algorithm always outputs a $(1-1/e)$-approximation to the expected number of adoptions in the optimal non-adaptive seed choice.
Social and Information Networks
Efficient Inexact Proximal Gradient Algorithm for Nonconvex Problems
The proximal gradient algorithm has been popularly used for convex optimization.
Optimization and Control
On Adaptivity Gaps of Influence Maximization under the Independent Cascade Model with Full Adoption Feedback
In this paper, we study the adaptivity gap of the influence maximization problem under independent cascade model when full-adoption feedback is available.
Social and Information Networks
Adaptive Expansion Bayesian Optimization for Unbounded Global Optimization
Bayesian optimization is normally performed within fixed variable bounds.
Combinatorial Semi-Bandit in the Non-Stationary Environment
In a special case where the reward function is linear and we have an exact oracle, we design a parameter-free algorithm that achieves nearly optimal regret both in the switching case and in the dynamic case without knowing the parameters in advance.
Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation
In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence.
Federated Machine Learning for Intelligent IoT via Reconfigurable Intelligent Surface
Intelligent Internet-of-Things (IoT) will be transformative with the advancement of artificial intelligence and high-dimensional data analysis, shifting from "connected things" to "connected intelligence".
Lightweight Mask R-CNN for Long-Range Wireless Power Transfer Systems
The proposed approach makes the object detection much easier to be transplanted on mobile devices and reduce the burden of hardware computation.
