Search Results for author:
Found 166 papers, 49 papers with code
Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.
Ranked #6 on
Speech Recognition
on AISHELL-1
WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit
In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.
WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit
Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model.
TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty
In this paper, we present TrimTail, a simple but effective emission regularization method to improve the latency of streaming ASR models.
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
We then propose an Architecture-Agnostic Masked Image Modeling framework (A$^2$MIM), which is compatible with both Transformers and CNNs in a unified way.
DPAUC: Differentially Private AUC Computation in Federated Learning
Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants.
Object Localization under Single Coarse Point Supervision
In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points.
Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes
Object detection via inaccurate bounding boxes supervision has boosted a broad interest due to the expensive high-quality annotation data or the occasional inevitability of low annotation quality (\eg tiny objects).
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i. e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework.
Ranked #8 on
Image Classification
on Places205
Exploring Localization for Self-supervised Fine-grained Contrastive Learning
Self-supervised contrastive learning has demonstrated great potential in learning visual representations.
Ranked #21 on
Fine-Grained Image Classification
on NABirds
GenURL: A General Framework for Unsupervised Representation Learning
For example, dimension reduction methods, t-SNE, and UMAP optimize pair-wise data relationships by preserving the global geometric structure, while self-supervised learning, SimCLR, and BYOL focus on mining the local statistics of instances under specific augmentations.
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Accordingly, we propose $\eta$-balanced mixup loss for complementary learning of the two sub-objectives.
Ranked #7 on
Image Classification
on Places205
DLME: Deep Local-flatness Manifold Embedding
To overcome the underconstrained embedding problem, we design a loss and theoretically demonstrate that it leads to a more suitable embedding based on the local flatness.
Ranked #2 on
Image Classification
on ImageNet-100
OpenMixup: A Comprehensive Mixup Benchmark for Visual Classification
Data mixing, or mixup, is a data-dependent augmentation technique that has greatly enhanced the generalizability of modern deep neural networks.
MogaNet: Multi-order Gated Aggregation Network
Notably, MogaNet hits 80. 0\% and 87. 8\% accuracy with 5. 2M and 181M parameters on ImageNet-1K, outperforming ParC-Net and ConvNeXt-L, while saving 59\% FLOPs and 17M parameters, respectively.
Ranked #1 on
Pose Estimation
on COCO val2017
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DNN) optimization.
WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total.
Ranked #5 on
Speech Recognition
on WenetSpeech
EasyQuant: Post-training Quantization via Scale Optimization
The 8 bits quantization has been widely applied to accelerate network inference in various deep learning applications.
Masked Modeling for Self-supervised Representation Learning on Vision and Beyond
As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data.
DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks
Motivation: Drug discovery demands rapid quantification of compound-protein interaction (CPI).
Ranked #2 on
Drug Discovery
on BindingDB IC50
End-to-End Learning for Simultaneously Generating Decision Map and Multi-Focus Image Fusion Result
In this work, to handle the requirements of both output image quality and comprehensive simplicity of structure implementation, we propose a cascade network to simultaneously generate decision map and fused result with an end-to-end training procedure.
6D-VNet: End-to-end 6DoF Vehicle Pose Estimation from Monocular RGB Images
We present a conceptually simple framework for 6DoF object pose estimation, especially for autonomous driving scenario.
FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning
Further, FedAdapt adopts reinforcement learning based optimization and clustering to adaptively identify which layers of the DNN should be offloaded for each individual device on to a server to tackle the challenges of computational heterogeneity and changing network bandwidth.
SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling
Slot filling and intent detection are two main tasks in spoken language understanding (SLU) system.
Lightweight Learner for Shared Knowledge Lifelong Learning
We propose a new Shared Knowledge Lifelong Learning (SKILL) challenge, which deploys a decentralized population of LL agents that each sequentially learn different tasks, with all agents operating independently and in parallel.
FedFly: Towards Migration in Edge-based Distributed Federated Learning
Our empirical results on the CIFAR10 dataset, with both balanced and imbalanced data distribution, support our claims that FedFly can reduce training time by up to 33% when a device moves after 50% of the training is completed, and by up to 45% when 90% of the training is completed when compared to state-of-the-art offloading approach in FL.
Time Series Anomaly Detection via Reinforcement Learning-Based Model Selection
Time series anomaly detection has been recognized as of critical importance for the reliable and efficient operation of real-world systems.
Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study
However, there lacks a systematic study of how the two types of approaches compare and how different design choices can affect the performance of PLM-based models.
Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Models
DeSel improves greedy search by an average of 4. 7% semantic F1 across five datasets.
On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generation
This study addresses the application of encoder-only Pre-trained Language Models (PLMs) in keyphrase generation (KPG) amidst the broader availability of domain-tailored encoder-only models compared to encoder-decoder models.
neuro2vec: Masked Fourier Spectrum Prediction for Neurophysiological Representation Learning
Extensive data labeling on neurophysiological signals is often prohibitively expensive or impractical, as it may require particular infrastructure or domain expertise.
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks
Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions.
CeBed: A Benchmark for Deep Data-Driven OFDM Channel Estimation
This work offers a comprehensive and unified framework to help researchers evaluate and design data-driven channel estimation algorithms.
Representation Learning for Resource-Constrained Keyphrase Generation
State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with limited annotated data.
Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach
In this work, we propose DTLight, a simple yet powerful lightweight Decision Transformer-based TSC method that can learn policy from easily accessible offline datasets.
Constrained Adaptive Projection with Pretrained Features for Anomaly Detection
Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection.
Ranked #8 on
Anomaly Detection
on One-class CIFAR-10
Challenges to Open-Domain Constituency Parsing
Neural constituency parsers have reached practical performance on news-domain benchmarks.
KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation
Despite the significant advancements in keyphrase extraction and keyphrase generation methods, the predominant approach for evaluation mainly relies on exact matching with human references.
Kernalised Multi-resolution Convnet for Visual Tracking
Visual tracking is intrinsically a temporal problem.
Unsupervised Deep Manifold Attributed Graph Embedding
Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space.
Ranked #2 on
Node Clustering
on Pubmed
Conditional Approximate Normalizing Flows for Joint Multi-Step Probabilistic Forecasting with Application to Electricity Demand
In this paper, we introduce the conditional approximate normalizing flow (CANF) to make probabilistic multi-step time-series forecasts when correlations are present over long time horizons.
FedDWA: Personalized Federated Learning with Dynamic Weight Adjustment
In this paper, we propose a new PFL algorithm called \emph{FedDWA (Federated Learning with Dynamic Weight Adjustment)} to address the above problem, which leverages the parameter server (PS) to compute personalized aggregation weights based on collected models from clients.
Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy
In this work, we study a crucial question which has been vastly overlooked by existing works: what are the optimal numbers of queries and replies in FL with DP so that the final model accuracy is maximized.
Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss
The deviation of a classification model is caused by both class-wise and attribute-wise imbalance.
Context-Aware Cross-Attention for Non-Autoregressive Translation
Non-autoregressive translation (NAT) significantly accelerates the inference process by predicting the entire target sequence.
Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models
To tackle this problem, we propose Sample Discrimination based Selection (SDS) to select efficient samples that could discriminate multiple models, i. e., the prediction behaviors (right/wrong) of these samples would be helpful to indicate the trend of model performance.
Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation
Using a vocabulary that is shared across languages is common practice in Multilingual Neural Machine Translation (MNMT).
HAIFIT: Human-Centered AI for Fashion Image Translation
Our method excels in preserving the distinctive style and intricate details essential for fashion design applications.
Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising
Our analysis shows that the immediate reward from environment is misleading under a critical resource constraint.
Machine Learning for Building Energy and Indoor Environment: A Perspective
It is indicated that the theories and applications of machine learning method in the field of energy conservation and indoor environment are not mature, due to the difficulty of the determination for model structure with better prediction.
A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising
With this formulation, we derive the optimal impression allocation strategy by solving the optimal bidding functions for contracts.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Random Occlusion-recovery for Person Re-identification
As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera.
Omni-directional Feature Learning for Person Re-identification
Most of them focus on learning the part feature representation of person body in horizontal direction.
WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition
In this work, we first use WordNet to understand and expand word embedding for settling the polysemy of homographic puns, and then propose a WordNet-Encoded Collocation-Attention network model (WECA) which combined with the context weights for recognizing the puns.
Robust and customized methods for real-time hand gesture recognition under object-occlusion
Dynamic hand tracking and gesture recognition is a hard task since there are many joints on the fingers and each joint owns many degrees of freedom.
Human-Computer Interaction
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition
Over the last few years, with the immense popularity of the Kinect, there has been renewed interest in developing methods for human gesture and action recognition from 3D skeletal data.
AI-Skin : Skin Disease Recognition based on Self-learning and Wide Data Collection through a Closed Loop Framework
First, the wide collection of data in the close-loop information flow of user and remote medical data center is discussed.
Attention Deep Model with Multi-Scale Deep Supervision for Person Re-Identification
Besides, most of the multi-scale models embedding the multi-scale feature learning block into the feature extraction deep network, which reduces the efficiency of inference network.
Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts
DeepRelations shows superior interpretability to the state-of-the-art: without compromising affinity prediction, it boosts the AUPRC of contact prediction 9. 5, 16. 9, 19. 3 and 5. 7-fold for the test, compound-unique, protein-unique, and both-unique sets, respectively.
DeepBrain: Towards Personalized EEG Interaction through Attentional and Embedded LSTM Learning
The "mind-controlling" capability has always been in mankind's fantasy.
Neural Mesh Refiner for 6-DoF Pose Estimation
We utilise the overlay between the accurate mask prediction and less accurate mesh prediction to iteratively optimise the direct regressed 6D pose information with a focus on translation estimation.
DeepC2: AI-powered Covert Command and Control on OSNs
The defender can limit the attacker once it is exposed.
When Deep Reinforcement Learning Meets Federated Learning: Intelligent Multi-Timescale Resource Management for Multi-access Edge Computing in 5G Ultra Dense Network
Ultra-dense edge computing (UDEC) has great potential, especially in the 5G era, but it still faces challenges in its current solutions, such as the lack of: i) efficient utilization of multiple 5G resources (e. g., computation, communication, storage and service resources); ii) low overhead offloading decision making and resource allocation strategies; and iii) privacy and security protection schemes.
Unsupervised Word Alignment via Cross-Lingual Contrastive Learning
Recently, the performance of the neural word alignment models has exceeded that of statistical models.
From Distributed Machine Learning To Federated Learning: In The View Of Data Privacy And Security
Federated learning is an improved version of distributed machine learning that further offloads operations which would usually be performed by a central server.
Distributed, Parallel, and Cluster Computing
On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times
Then, we theoretically derive: 1) the conditions for the DP based FedAvg to converge as the number of global iterations (GI) approaches infinity; 2) the method to set the number of local iterations (LI) to minimize the negative influence of DP noises.
MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning
Recently, the performance of the neural word alignment models has exceeded that of statistical models.
Virtual Reality: A Survey of Enabling Technologies and its Applications in IoT
Virtual Reality (VR) has shown great potential to revolutionize the market by providing users immersive experiences with freedom of movement.
Networking and Internet Architecture
Representation range needs for 16-bit neural network training
While neural networks have been trained using IEEE-754 binary32 arithmetic, the rapid growth of computational demands in deep learning has boosted interest in faster, low precision training.
Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding
Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
Environment-Aware and Training-Free Beam Alignment for mmWave Massive MIMO via Channel Knowledge Map
Two instances of CKM are proposed for beam alignment in mmWave massive MIMO systems, namely channel path map (CPM) and beam index map (BIM).
Energy Model for UAV Communications: Experimental Validation and Model Generalization
In this paper, via extensive flight experiments, we aim to firstly validate the recently derived theoretical energy model for rotary-wing UAVs, and then develop a general model for those complicated flight scenarios where rigorous theoretical model derivation is quite challenging, if not impossible.
Software-Defined Edge Computing: A New Architecture Paradigm to Support IoT Data Analysis
We further present an experiment on data anomaly detection in this architecture, and the comparison between two architectures for ECG diagnosis.
U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition
On the experiment of AISHELL-1, we achieve a 4. 63\% character error rate (CER) with a non-streaming setup and 5. 05\% with a streaming setup with 320ms latency by U2++.
Data-driven Model Predictive and Reinforcement Learning Based Control for Building Energy Management: a Survey
Building energy management is one of the core problems in modern power grids to reduce energy consumption while ensuring occupants' comfort.
Time Series Anomaly Detection for Smart Grids: A Survey
With the rapid increase in the integration of renewable energy generation and the wide adoption of various electric appliances, power grids are now faced with more and more challenges.
The USYD-JD Speech Translation System for IWSLT 2021
Our constrained system is based on a pipeline framework, i. e. ASR and NMT.
Improving Neural Machine Translation by Bidirectional Training
We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation.
Improving Discriminative Visual Representation Learning via Automatic Mixup
In this paper, we decompose mixup into two sub-tasks of mixup generation and classification and formulate it for discriminative representations as class- and instance-level mixup.
Benchmarking Sample Selection Strategies for Batch Reinforcement Learning
Through extensive experiments on the standard batch RL datasets, we find that non-uniform sampling is also effective in batch RL settings.
Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning
Unfortunately, most online reinforcement learning algorithms require a large number of interactions with the environment to learn a reliable control policy.
C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction.
ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control
Traffic signal control is of critical importance for the effective use of transportation infrastructures.
P2P-Loc: Point to Point Tiny Person Localization
As a result, we propose a point self-refinement approach that iteratively updates point annotations in a self-paced way.
Gap Minimization for Knowledge Sharing and Transfer
Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e. g., $\mathcal{H}$-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees.
Learning to Simulate Unseen Physical Systems with Graph Neural Networks
Simulation of the dynamics of physical systems is essential to the development of both science and engineering.
Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation
The proposed training scheme significantly improves the performance of patient-specific seizure predictors and bridges the gap between patient-specific and patient-independent predictors.
Network Anomaly Detection Using Federated Learning and Transfer Learning
In the second learning stage, Ot uses the transfer learning method to reconstruct and re-train the model to further improve the detection performance on the specific task.
Impression Allocation and Policy Search in Display Advertising
In order to address the unstable traffic pattern challenge and achieve the optimal overall outcome, we propose a multi-agent reinforcement learning method to adjust the bids from each guaranteed contract, which is simple, converging efficiently and scalable.
Self-training semi-supervised classification based on density peaks of data
Having a multitude of unlabeled data and few labeled ones is a common problem in many practical ap- plications.
Predicting Peak Day and Peak Hour of Electricity Demand with Ensemble Machine Learning
In this study, we develop a supervised machine learning approach to generate 1) the probability of the next operation day containing the peak hour of the month and 2) the probability of an hour to be the peak hour of the day.
A Differential Evolution-Enhanced Latent Factor Analysis Model for High-dimensional and Sparse Data
High-dimensional and sparse (HiDS) matrices are frequently adopted to describe the complex relationships in various big data-related systems and applications.
Graph-incorporated Latent Factor Analysis for High-dimensional and Sparse Matrices
A High-dimensional and sparse (HiDS) matrix is frequently encountered in a big data-related application like an e-commerce system or a social network services system.
A Multi-Metric Latent Factor Model for Analyzing High-Dimensional and Sparse data
High-dimensional and sparse (HiDS) matrices are omnipresent in a variety of big data-related applications.
Meta-Learning Based Early Fault Detection for Rolling Bearings via Few-Shot Anomaly Detection
To address this problem, many transfer learning based EFD methods utilize historical data to learn transferable domain knowledge and conduct early fault detection on new target bearings.
An Early Fault Detection Method of Rotating Machines Based on Multiple Feature Fusion with Stacking Architecture
One of the key points of EFD is developing a generic model to extract robust and discriminative features from different equipment for early fault detection.
Differentially Private AUC Computation in Vertical Federated Learning
In this work, we propose two evaluation algorithms that can more accurately compute the widely used AUC (area under curve) metric when using label DP in vFL.
MALICE: Manipulation Attacks on Learned Image ComprEssion
To characterize the robustness of state-of-the-art learned image compression, we mount white-box and black-box attacks.
HIFI-Net: A Novel Network for Enhancement to Underwater Images
As this network make "Haar Images into Fusion Images", it is called HIFI-Net.
Energy Storage State-of-Charge Market Model
Combined with an optimal bidding design algorithm using dynamic programming, our paper shows that the SoC segment market model provides more accurate representations of the opportunity costs of energy storage compared to existing power-based bidding models.
An Online Sparse Streaming Feature Selection Algorithm
In many real applications such as intelligent healthcare platform, streaming feature always has some missing data, which raises a crucial challenge in conducting OSFS, i. e., how to establish the uncertain relationship between sparse streaming features and labels.
Optimal Measurement of Drone Swarm in RSS-based Passive Localization with Region Constraints
In this paper, optimal geometrical configurations of UAVs in received signal strength (RSS)-based localization under region constraints are investigated.
An Adam-adjusting-antennae BAS Algorithm for Refining Latent Factors
The A2BAS algorithm consists of two sub-algorithms.
A Latent Feature Analysis-based Approach for Spatio-Temporal Traffic Data Recovery
In the past decade, scholars have done many research on the recovery of missing traffic data, however how to make full use of spatio-temporal traffic patterns to improve the recovery performance is still an open problem.
Reinforcement Learning Based Dynamic Model Combination for Time Series Forecasting
To deal with this challenge, we propose a reinforcement learning (RL) based model combination (RLMC) framework for determining model weights in an ensemble for time series forecasting tasks.
FedMCSA: Personalized Federated Learning via Model Components Self-Attention
Federated learning (FL) facilitates multiple clients to jointly train a machine learning model without sharing their private data.
An ICA-Based HVAC Load Disaggregation Method Using Smart Meter Data
The residual load profiles are processed using ICA for HVAC load extraction.
Deep Koopman Learning of Nonlinear Time-Varying Systems
This paper presents a data-driven approach to approximate the dynamics of a nonlinear time-varying system (NTVS) by a linear time-varying system (LTVS), which is resulted from the Koopman operator and deep neural networks.
Transfer Learning on Electromyography (EMG) Tasks: Approaches and Beyond
In this survey, we assess the eligibility of more than fifty published peer-reviewed representative transfer learning approaches for EMG applications.
MetaEMS: A Meta Reinforcement Learning-based Control Framework for Building Energy Management System
The building sector has been recognized as one of the primary sectors for worldwide energy consumption.
An Iterative Bidirectional Gradient Boosting Approach for CVR Baseline Estimation
In contrast to many existing methods, we treat CVR baseline estimation as a missing data retrieval problem.
Dual Class-Aware Contrastive Federated Semi-Supervised Learning
To our knowledge, we are the first to present an FSSL method that utilizes only 10\% labeled clients, while still achieving superior performance compared to standard federated supervised learning, which uses all clients with labeled data.
Load Profile Inpainting for Missing Load Data Restoration and Baseline Estimation
We propose a Generator structure consisting of a coarse network and a fine-tuning network.
A Modified Sequence-to-point HVAC Load Disaggregation Algorithm
This paper presents a modified sequence-to-point (S2P) algorithm for disaggregating the heat, ventilation, and air conditioning (HVAC) load from the total building electricity consumption.
Relightable Neural Human Assets from Multi-view Gradient Illuminations
UltraStage will be publicly available to the community to stimulate significant future developments in various human modeling and rendering tasks.
Design Considerations of a Coordinative Demand Charge Mitigation Strategy
This paper presents a coordinative demand charge mitigation (DCM) strategy for reducing electricity consumption during system peak periods.
Original or Translated? On the Use of Parallel Data for Translation Quality Estimation
Machine Translation Quality Estimation (QE) is the task of evaluating translation output in the absence of human-written references.
Multi-Metric AutoRec for High Dimensional and Sparse User Behavior Data Prediction
The idea of the proposed MMA is mainly two-fold: 1) apply different $L_p$-norm on loss function and regularization to form different variant models in different metric spaces, and 2) aggregate these variant models.
A Novel Modular, Reconfigurable Battery Energy Storage System: Design, Control, and Experimentation
An optimal power management approach is developed to extensively exploit the merits of the proposed design.
Self-Supervised Transformer Architecture for Change Detection in Radio Access Networks
Such networks undergo frequent and often heterogeneous changes caused by network operators, who are seeking to tune their system parameters for optimal performance.
Adaptive Aggregation for Safety-Critical Control
Safety has been recognized as the central obstacle to preventing the use of reinforcement learning (RL) for real-world applications.
Online Sparse Streaming Feature Selection Using Adapted Classification
Traditional feature selections need to know the feature space before learning, and online streaming feature selection (OSFS) is proposed to process streaming features on the fly.
Anomaly Detection with Ensemble of Encoder and Decoder
Usually, machine learning-based methods need to model the normal data distribution.
Multi-agent Attention Actor-Critic Algorithm for Load Balancing in Cellular Networks
In cellular networks, User Equipment (UE) handoff from one Base Station (BS) to another, giving rise to the load balancing problem among the BSs.
From Wide to Deep: Dimension Lifting Network for Parameter-efficient Knowledge Graph Embedding
To seek a simple strategy to improve the parameter efficiency of conventional KGE models, we take inspiration from that deeper neural networks require exponentially fewer parameters to achieve expressiveness comparable to wider networks for compositional structures.
Edge-Based Video Analytics: A Survey
Edge computing has been getting a momentum with ever-increasing data at the edge of the network.
Policy Reuse for Communication Load Balancing in Unseen Traffic Scenarios
When deploying to an unknown traffic scenario, we select a policy from the policy bank based on the similarity between the previous-day traffic of the current scenario and the traffic observed during training.
Communication Load Balancing via Efficient Inverse Reinforcement Learning
Engineering this reward function is challenging, because it involves the need for expert knowledge and there lacks a general consensus on the form of an optimal reward function.
BARA: Efficient Incentive Mechanism with Online Reward Budget Allocation in Cross-Silo Federated Learning
The challenge of this problem lies in the opaque feedback between reward budget allocation and model utility improvement of FL, making the optimal reward budget allocation complicated.
ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling
Recent years have witnessed significant developments in point cloud processing, including classification and segmentation.
ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs
In this paper, we present ZeroPrompt (Figure 1-(a)) and the corresponding Prompt-and-Refine strategy (Figure 3), two simple but effective \textbf{training-free} methods to decrease the Token Display Time (TDT) of streaming ASR models \textbf{without any accuracy loss}.
A new sulfur bioconversion process development for energy- and space-efficient secondary wastewater treatment
Typical pretreated wastewater was synthesized with chemical oxygen demand of 110 mg/L, sulfate of 50 mg S/L, and varying dissolved oxygen (DO) and was fed into a moving-bed biofilm reactor (MBBR).
Asymptotic Performance Analysis of Large-Scale Active IRS-Aided Wireless Network
Numerical simulation results show that a 3-bit discrete phase shifter is required to achieve a trivial performance loss for a large-scale active IRS.
An Error Correction Mid-term Electricity Load Forecasting Model Based on Seasonal Decomposition
Then, based on the idea of stacking ensemble, long short-term memory is employed as an error correction module to forecast the components separately, and the forecast results are treated as new features to be fed into extreme gradient boosting for the second-step forecasting.
Active learning for effective Hamiltonian of super-large-scale atomic structures
However, the parametrization method of the effective Hamiltonian is complicated and hardly can resolve the systems with complex interactions and/or complex components.
Virtual histological staining of unlabeled autopsy tissue
Histological examination is a crucial step in an autopsy; however, the traditional histochemical staining of post-mortem samples faces multiple challenges, including the inferior staining quality due to autolysis caused by delayed fixation of cadaver tissue, as well as the resource-intensive nature of chemical staining procedures covering large tissue areas, which demand substantial labor, cost, and time.
A Read Margin Enhancement Circuit with Dynamic Bias Optimization for MRAM
This brief introduces a read bias circuit to improve readout yield of magnetic random access memories (MRAMs).
UvA-MT's Participation in the WMT23 General Translation Shared Task
This paper describes the UvA-MT's submission to the WMT 2023 shared task on general machine translation.
Adaptive Dynamic Programming for Energy-Efficient Base Station Cell Switching
In this work, we propose an approximate dynamic programming (ADP)-based method coupled with online optimization to switch on/off the cells of base stations to reduce network power consumption while maintaining adequate Quality of Service (QoS) metrics.
Enhancing Building Energy Efficiency through Advanced Sizing and Dispatch Methods for Energy Storage
The solution is determined considering both capital costs in optimal sizing and operational benefits in optimal dispatch.
A Better Match for Drivers and Riders: Reinforcement Learning at Lyft
This change was the first documented implementation of a ridesharing matching algorithm that can learn and improve in real time.
Online Two-stage Thermal History Prediction Method for Metal Additive Manufacturing of Thin Walls
With measured/predicted temperature profiles of several points on the same layer, the second stage proposes a reduced order model (ROM) (intra-layer prediction model) to decompose and construct the temperature profiles of all points on the same layer, which could be used to build the temperature field of the entire layer.
Scalable Optimal Power Management for Large-Scale Battery Energy Storage Systems
Since the number of clusters is much fewer than the number of cells, the proposed approach significantly reduces the computational costs, allowing optimal power management to scale up to large-scale BESS.
Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Training
We seminally propose the concept of Shock Absorber (a type of perturbation) that enhances the robustness and stability of the original graphs against changes in an adversarial training fashion.
Anomaly Detection for Scalable Task Grouping in Reinforcement Learning-based RAN Optimization
This coincides with a rapid increase in the number of cell sites worldwide, driven largely by dramatic growth in cellular network traffic.
Neural Network Approximation for Pessimistic Offline Reinforcement Learning
In this paper, we establish a non-asymptotic estimation error of pessimistic offline RL using general neural network approximation with $\mathcal{C}$-mixing data regarding the structure of networks, the dimension of datasets, and the concentrability of data coverage, under mild assumptions.
A Split-and-Privatize Framework for Large Language Model Fine-Tuning
Fine-tuning is a prominent technique to adapt a pre-trained language model to downstream scenarios.
On the Selection of Intermediate Length Representative Periods for Capacity Expansion
To this end, we propose a novel method for selecting representative periods of any length.
Hallucination Detection and Hallucination Mitigation: An Investigation
Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved remarkable successes over the last two years in a range of different applications.
A Joint Multi-Gradient Algorithm for Demosaicing Bayer Images
Experiments show that the algorithm in this paper has better recovery in image edges as well as texture complex regions with higher PSNR and SSIM values and better subjective visual perception compared to the traditional gradient algorithms such as BI, Cok, Hibbard, Laroche, Hamiton, while the algorithm involves only the add-subtract and shift operations, which is suitable to be implemented on the hardware platform.
How Far Can 100 Samples Go? Unlocking Overall Zero-Shot Multilingual Translation via Tiny Multi-Parallel Data
Zero-shot translation aims to translate between language pairs not seen during training in Multilingual Machine Translation (MMT) and is largely considered an open problem.
A Systematic Literature Review on Explainability for Machine/Deep Learning-based Software Engineering Research
The remarkable achievements of Artificial Intelligence (AI) algorithms, particularly in Machine Learning (ML) and Deep Learning (DL), have fueled their extensive deployment across multiple sectors, including Software Engineering (SE).
Analysis of Knowledge Tracing performance on synthesised student data
Knowledge Tracing (KT) aims to predict the future performance of students by tracking the development of their knowledge states.
Graph Attention-based Reinforcement Learning for Trajectory Design and Resource Assignment in Multi-UAV Assisted Communication
In this paper, a novel graph-attention multi-agent trust region (GA-MATR) reinforcement learning framework is proposed to solve the multi-UAV assisted communication problem.
G4G:A Generic Framework for High Fidelity Talking Face Generation with Fine-grained Intra-modal Alignment
Despite numerous completed studies, achieving high fidelity talking face generation with highly synchronized lip movements corresponding to arbitrary audio remains a significant challenge in the field.
Meta-Task Prompting Elicits Embedding from Large Language Models
In this work, we introduce a new unsupervised embedding method, Meta-Task Prompting with Explicit One-Word Limitation (MetaEOL), for generating high-quality sentence embeddings from Large Language Models (LLMs) without the need for model fine-tuning or task-specific engineering.
NoteLLM: A Retrievable Large Language Model for Note Recommendation
Indeed, learning to generate hashtags/categories can potentially enhance note embeddings, both of which compress key note information into limited content.
Qubit-Wise Architecture Search Method for Variational Quantum Circuits
Considering the noise level limit, one crucial aspect for quantum machine learning is to design a high-performing variational quantum circuit architecture with small number of quantum gates.
Prototyping and Experimental Results for Environment-Aware Millimeter Wave Beam Alignment via Channel Knowledge Map
In this paper, to alleviate the large training overhead in millimeter wave (mmWave) beam alignment, an environment-aware and training-free beam alignment prototype is established based on a typical CKM, termed beam index map (BIM).
Repoformer: Selective Retrieval for Repository-Level Code Completion
Recent advances in retrieval-augmented generation (RAG) have initiated a new era in repository-level code completion.
BRIEDGE: EEG-Adaptive Edge AI for Multi-Brain to Multi-Robot Interaction
To better extract the joint features of heterogeneous EEG data as well as enhance classification accuracy, BRIEDGE introduces an informer-based ProbSparse self-attention mechanism.
ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching
In a single GPU-CPU system, we demonstrate that under varying workloads, ALISA improves the throughput of baseline systems such as FlexGen and vLLM by up to 3X and 1. 9X, respectively.
Neuron Specialization: Leveraging intrinsic task modularity for multilingual machine translation
Training a unified multilingual model promotes knowledge transfer but inevitably introduces negative interference.
An Online Spatial-Temporal Graph Trajectory Planner for Autonomous Vehicles
Among these modules, the trajectory planner plays a pivotal role in the safety of the vehicle and the comfort of its passengers.
FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning
Subgraph federated learning (subgraph-FL) is a new distributed paradigm that facilitates the collaborative training of graph neural networks (GNNs) by multi-client subgraphs.
