Search Results for author:
Found 60 papers, 23 papers with code
TNT: Text Normalization based Pre-training of Transformers for Content Moderation
In this work, we present a new language pre-training model TNT (Text Normalization based pre-training of Transformers) for content moderation.
Causal Invariance Learning via Efficient Optimization of a Nonconvex Objective
To address both challenges, we focus on the additive intervention regime and propose nearly necessary and sufficient conditions for ensuring that the invariant prediction model matches the causal outcome model.
Multi-modal and Multi-scale Spatial Environment Understanding for Immersive Visual Text-to-Speech
The multi-modal aims to take both the RGB and Depth spaces of the spatial image to learn more comprehensive spatial information, and the multi-scale seeks to model the local and global spatial knowledge simultaneously.
Emphasis Rendering for Conversational Text-to-Speech with Multi-modal Multi-scale Context Modeling
In this paper, we propose a novel Emphasis Rendering scheme for the CTTS model, termed ER-CTTS, that includes two main components: 1) we simultaneously take into account textual and acoustic contexts, with both global and local semantic modeling to understand the conversation context comprehensively; 2) we deeply integrate multi-modal and multi-scale context to learn the influence of context on the emphasis expression of the current utterance.
TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting
Eliminating non-stationarity is essential for avoiding spurious regressions and capturing local dependencies in short-term modeling, while preserving it is crucial for revealing long-term cointegration across variates.
MCI-GRU: Stock Prediction Model Based on Multi-Head Cross-Attention and Improved GRU
Existing approaches also generally struggle to capture unobservable latent market states effectively, such as market sentiment and expectations, microstructural factors, and participant behavior patterns, leading to an inadequate understanding of market dynamics and subsequently impact prediction accuracy.
Landscape of Policy Optimization for Finite Horizon MDPs with General State and Action
Policy gradient methods are widely used in reinforcement learning.
LSR-IGRU: Stock Trend Prediction Based on Long Short-Term Relationships and Improved GRU
However, existing methods mostly focus on the short-term dynamic relationships of stocks and directly integrating relationship information with temporal information.
Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles
This setting captures various optimization paradigms, such as conditional stochastic optimization, distributionally robust optimization, shortfall risk optimization, and machine learning paradigms, such as contrastive learning.
Generative Expressive Conversational Speech Synthesis
After that, the expressive conversational speech is synthesized by the conversation-enriched VITS to deliver feedback to the user. Furthermore, we propose a large-scale Natural CSS Dataset called NCSSD, that includes both naturally recorded conversational speech in improvised styles and dialogues extracted from TV shows.
Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models
The location of knowledge within Generative Pre-trained Transformer (GPT)-like models has seen extensive recent investigation.
Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting
Transformer-based and MLP-based methods have emerged as leading approaches in time series forecasting (TSF).
Ranked #14 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Contextual Bilevel Reinforcement Learning for Incentive Alignment
We empirically demonstrate the performance of our algorithm for reward shaping and tax design.
Group Robust Preference Optimization in Reward-free RLHF
Our approach builds upon reward-free direct preference optimization methods, but unlike previous approaches, it seeks a robust policy which maximizes the worst-case group performance.
Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data
We develop and analyze algorithms for instrumental variable regression by viewing the problem as a conditional stochastic optimization problem.
Understanding the Functional Roles of Modelling Components in Spiking Neural Networks
By designing and evaluating several variants of the classic model, we systematically investigate the functional roles of key modelling components, leakage, reset, and recurrence, in leaky integrate-and-fire (LIF) based SNNs.
Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling
Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting.
Distributionally Robust Model-based Reinforcement Learning with Large State Spaces
Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment deployment.
Deep Directly-Trained Spiking Neural Networks for Object Detection
Spiking neural networks (SNNs) are brain-inspired energy-efficient models that encode information in spatiotemporal dynamics.
Deep-Learning Tool for Early Identifying Non-Traumatic Intracranial Hemorrhage Etiology based on CT Scan
Conclusions: The proposed deep learning algorithms can be an effective tool for early identification of hemorrhage etiologies based on NCCT scans.
CRYPTEXT: Database and Interactive Toolkit of Human-Written Text Perturbations in the Wild
CRYPTEXT is a data-intensive application that provides the users with a database and several tools to extract and interact with human-written perturbations.
Deep-Reinforcement-Learning-based Path Planning for Industrial Robots using Distance Sensors as Observation
Industrial robots are widely used in various manufacturing environments due to their efficiency in doing repetitive tasks such as assembly or welding.
MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Dataset
Text-to-Speech (TTS) synthesis for low-resource languages is an attractive research issue in academia and industry nowadays.
FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis
Therefore, we propose a novel expressive conversational TTS model, termed as FCTalker, that learn the fine and coarse grained context dependency at the same time during speech generation.
Attention Spiking Neural Networks
On ImageNet-1K, we achieve top-1 accuracy of 75. 92% and 77. 08% on single/4-step Res-SNN-104, which are state-of-the-art results in SNNs.
MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline
This paper introduces a high-quality open-source text-to-speech (TTS) synthesis dataset for Mongolian, a low-resource language spoken by over 10 million people worldwide.
BSDGAN: Balancing Sensor Data Generative Adversarial Networks for Human Activity Recognition
However, due to the inconsistent frequency of human activities, the amount of data for each activity in the human activity dataset is imbalanced.
SmartGD: A GAN-Based Graph Drawing Framework for Diverse Aesthetic Goals
There are a few existing methods that have attempted to develop a flexible solution for optimizing different aesthetic aspects measured by different aesthetic criteria.
Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization
We further study the algorithm-dependent generalization bounds via stability arguments of algorithms.
Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense
We find that adversarial texts generated by ANTHRO achieve the best trade-off between (1) attack success rate, (2) semantic preservation of the original text, and (3) stealthiness--i. e. indistinguishable from human writings hence harder to be flagged as suspicious.
MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learning
Accurate understanding of users in terms of predicative segments play an essential role in the day to day operation of modern internet enterprises.
SuperCone: Unified User Segmentation over Heterogeneous Experts via Concept Meta-learning
We study the problem of user segmentation: given a set of users and one or more predefined groups or segments, assign users to their corresponding segments.
Rethinking Pretraining as a Bridge from ANNs to SNNs
In this work, a new SNN training paradigm is proposed by combining the concepts of the two different training methods with the help of the pretrain technique and BP-based deep SNN training mechanism.
Advancing Spiking Neural Networks towards Deep Residual Learning
Despite the rapid progress of neuromorphic computing, inadequate capacity and insufficient representation power of spiking neural networks (SNNs) severely restrict their application scope in practice.
Advancing Deep Residual Learning by Solving the Crux of Degradation in Spiking Neural Networks
In this paper, we identify the crux and then propose a novel residual block for SNNs, which is able to significantly extend the depth of directly trained SNNs, e. g., up to 482 layers on CIFAR-10 and 104 layers on ImageNet, without observing any slight degradation problem.
On the Bias-Variance-Cost Tradeoff of Stochastic Optimization
We consider stochastic optimization when one only has access to biased stochastic oracles of the objective, and obtaining stochastic gradients with low biases comes at high costs.
BERT-Beta: A Proactive Probabilistic Approach to Text Moderation
Text moderation for user generated content, which helps to promote healthy interaction among users, has been widely studied and many machine learning models have been proposed.
TSI: an Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity
To realize this opportunity, we propose an ad text strength indicator (TSI) which: (i) predicts the click-through-rate (CTR) for an input ad text, (ii) fetches similar existing ads to create a neighborhood around the input ad, (iii) and compares the predicted CTRs in the neighborhood to declare whether the input ad is strong or weak.
DeepGD: A Deep Learning Framework for Graph Drawing Using GNN
In this paper, we propose a Convolutional Graph Neural Network based deep learning framework, DeepGD, which can draw arbitrary graphs once trained.
Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent
A novel ring FL topology as well as a map-reduce based synchronizing method are designed in the proposed RDFL to improve decentralized FL performance and bandwidth utilization.
What's in a Name? -- Gender Classification of Names with Character Based Machine Learning Models
Gender information is no longer a mandatory input when registering for an account at many leading Internet companies.
Political Posters Identification with Appearance-Text Fusion
In this paper, we propose a method that efficiently utilizes appearance features and text vectors to accurately classify political posters from other similar political images.
Going Deeper With Directly-Trained Larger Spiking Neural Networks
To this end, we propose a threshold-dependent batch normalization (tdBN) method based on the emerging spatio-temporal backpropagation, termed "STBP-tdBN", enabling direct training of a very deep SNN and the efficient implementation of its inference on neuromorphic hardware.
GFL: A Decentralized Federated Learning Framework Based On Blockchain
Federated learning(FL) is a rapidly growing field and many centralized and decentralized FL frameworks have been proposed.
HABERTOR: An Efficient and Effective Deep Hatespeech Detector
HABERTOR inherits BERT's architecture, but is different in four aspects: (i) it generates its own vocabularies and is pre-trained from the scratch using the largest scale hatespeech dataset; (ii) it consists of Quaternion-based factorized components, resulting in a much smaller number of parameters, faster training and inferencing, as well as less memory usage; (iii) it uses our proposed multi-source ensemble heads with a pooling layer for separate input sources, to further enhance its effectiveness; and (iv) it uses a regularized adversarial training with our proposed fine-grained and adaptive noise magnitude to enhance its robustness.
Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference
The neural attention mechanism plays an important role in many natural language processing applications.
Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations
In deep learning era, pretrained models play an important role in medical image analysis, in which ImageNet pretraining has been widely adopted as the best way.
Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning
To this end, self-supervised learning (SSL), as a potential solution for deficient annotated data, attracts increasing attentions from the community.
Multi-Modality Generative Adversarial Networks with Tumor Consistency Loss for Brain MR Image Synthesis
We use the synthesized modalities by TC-MGAN to boost the tumor segmentation accuracy, and the results demonstrate its effectiveness.
Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning
Conditional stochastic optimization covers a variety of applications ranging from invariant learning and causal inference to meta-learning.
A Deep Structural Model for Analyzing Correlated Multivariate Time Series
The seasonality component is approximated via a non-liner function of a set of Fourier terms, and the event components are learned by a simple linear function of regressor encoding the event dates.
Large-scale Gender/Age Prediction of Tumblr Users
In this paper, we propose graph based and deep learning models for age and gender predictions, which take into account user activities and content features.
Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization
As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with high efficiency.
Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube
Witnessed the development of deep learning, increasing number of studies try to build computer aided diagnosis systems for 3D volumetric medical data.
A GLCM Embedded CNN Strategy for Computer-aided Diagnosis in Intracerebral Hemorrhage
Computer-aided diagnosis (CADx) systems have been shown to assist radiologists by providing classifications of all kinds of medical images like Computed tomography (CT) and Magnetic resonance (MR).
Sample Complexity of Sample Average Approximation for Conditional Stochastic Optimization
In this paper, we study a class of stochastic optimization problems, referred to as the \emph{Conditional Stochastic Optimization} (CSO), in the form of $\min_{x \in \mathcal{X}} \EE_{\xi}f_\xi\Big({\EE_{\eta|\xi}[g_\eta(x,\xi)]}\Big)$, which finds a wide spectrum of applications including portfolio selection, reinforcement learning, robust learning, causal inference and so on.
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.
Nationality Classification Using Name Embeddings
Through our analysis of 57M contact lists from a major Internet company, we are able to design a fine-grained nationality classifier covering 39 groups representing over 90% of the world population.
HARP: Hierarchical Representation Learning for Networks
We present HARP, a novel method for learning low dimensional embeddings of a graph's nodes which preserves higher-order structural features.
Social and Information Networks
