Search Results for author:
Found 94 papers, 27 papers with code
Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision
Besides, the robustness of the previous neural methods is limited by the large-scale annotated data.
Incorporating Instructional Prompts into a Unified Generative Framework for Joint Multiple Intent Detection and Slot Filling
Specifically, we design 5-type templates as instructional prompts, and each template includes a question that acts as the driver to teach UGEN to grasp the paradigm, options that list the candidate intents or slots to reduce the answer search space, and the context denotes original utterance.
SkipBERT: Efficient Inference with Shallow Layer Skipping
In this paper, we propose SkipBERT to accelerate BERT inference by skipping the computation of shallow layers.
Deep Metric Tensor Regularized Policy Gradient
Armed with these technical developments, we propose a new policy gradient algorithm that learns to minimize the absolute divergence in the Riemannian manifold as an important regularization mechanism, allowing the Riemannian manifold to smoothen its policy gradient vector field.
Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility
With most of the related literature in the era of LLM uncharted, we propose an automated workflow that copes with an upscaled number of queries/responses.
Deep Partial Multi-Label Learning with Graph Disambiguation
In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels.
Controllable Textual Inversion for Personalized Text-to-Image Generation
The recent large-scale generative modeling has attained unprecedented performance especially in producing high-fidelity images driven by text prompts.
Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flow
In motion adaptation, we utilize the flow consistency knowledge to align the cross-domain optical flows into a motion-invariance common space, where the optical flow from clean weather is used as the guidance-knowledge to obtain a preliminary optical flow for adverse weather.
Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting
In order to address this issue, we propose GAS, a \shorten approach that can successfully adapt existing robust AGRs to non-IID settings.
FLAC: A Robust Failure-Aware Atomic Commit Protocol for Distributed Transactions
Consequently, it improves both the response time and throughput, and effectively handles nodes distributed across the Internet where crash and network failures might occur.
ACQ: Improving Generative Data-free Quantization Via Attention Correction
This is always ignored and restricts the quantization performance.
Speed up the inference of diffusion models via shortcut MCMC sampling
Diffusion probabilistic models have generated high quality image synthesis recently.
Unbiased Knowledge Distillation for Recommendation
Traditional solutions first train a full teacher model from the training data, and then transfer its knowledge (\ie \textit{soft labels}) to supervise the learning of a compact student model.
MSRL: Distributed Reinforcement Learning with Dataflow Fragments
Yet, current distributed RL systems tie the definition of RL algorithms to their distributed execution: they hard-code particular distribution strategies and only accelerate specific parts of the computation (e. g. policy network updates) on GPU workers.
Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training
In this paper, we propose a new technique to train an ensemble of base learners based on an innovative multi-step integration method.
SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth.
Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?
In the experiments, we develop a system with a less powerful stereo matching predictor and adopt the proposed refinement schemes to improve the accuracy.
The Metaverse Data Deluge: What Can We Do About It?
In the Metaverse, the physical space and the virtual space co-exist, and interact simultaneously.
Interpretable Fault Diagnosis of Rolling Element Bearings with Temporal Logic Neural Network
Machine learning-based methods have achieved successful applications in machinery fault diagnosis.
PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.
Where to Look: A Unified Attention Model for Visual Recognition with Reinforcement Learning
For example, we need the Gaussian policy with high variance to explore object of interests in a large image, which may cause randomized search and unstable learning.
Unifying Top-down and Bottom-up for Recurrent Visual Attention
For example, we need the Gaussian policy with high variance to explore object of interests in a large image, which may cause randomized search and unstable learning.
Contrastive Label Disambiguation for Partial Label Learning
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.
Towards Robust Cross-domain Image Understanding with Unsupervised Noise Removal
In multimedia analysis, domain adaptation studies the problem of cross-domain knowledge transfer from a label rich source domain to a label scarce target domain, thus potentially alleviates the annotation requirement for deep learning models.
SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis
Specifically, in terms of usability, it is demanding for non-experts to implement deep learning models, obtain the right settings for the entire machine learning pipeline, manage models and datasets, and exploit external data sources all together.
Deep Reinforcement Learning based Dynamic Optimization of Bus Timetable
Building on an existing method for calculating the carrying capacity, we develop a new technique to enhance the matching degree at each bus station.
ARM-Net: Adaptive Relation Modeling Network for Structured Data
The key idea is to model feature interactions with cross features selectively and dynamically, by first transforming the input features into exponential space, and then determining the interaction order and interaction weights adaptively for each cross feature.
Joining datasets via data augmentation in the label space for neural networks
Most, if not all, modern deep learning systems restrict themselves to a single dataset for neural network training and inference.
A critical look at the current train/test split in machine learning
The establishment of these split protocols are based on two assumptions: (i)-fixing the dataset to be eternally static so we could evaluate different machine learning algorithms or models; (ii)-there is a complete set of annotated data available to researchers or industrial practitioners.
Effective Slot Filling via Weakly-Supervised Dual-Model Learning
By using some particular weakly-labeled data, namely the plain phrases included in sentences, we propose a weaklysupervised slot filling approach.
Machine vision detection to daily facial fatigue with a nonlocal 3D attention network
Our experimental results in multiple metrics proved that our framework captured some typical, micro and dynamic facial features along spatiotemporal dimensions, contributing to the mild fatigue detection in the wild.
AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment
In this paper, we introduce a new class of alphas to model scalar, vector, and matrix features which possess the strengths of these two existing classes.
Thermally Regenerative Flow Batteries with pH Neutral Electrolytes for Harvesting Low-Grade Heat
This work also presents a comprehensive model with a coupled analysis of mass transfer and reaction kinetics in a porous electrode that can accurately capture the flow rate dependence of power density and energy conversion efficiency.
Applied Physics Classical Physics
Guided Interpolation for Adversarial Training
To enhance adversarial robustness, adversarial training learns deep neural networks on the adversarial variants generated by their natural data.
Multi-Agent Deep Reinforcement Learning for Request Dispatching in Distributed-Controller Software-Defined Networking
Recently, distributed controller architectures have been quickly gaining popularity in Software-Defined Networking (SDN).
Practical development of efficient thermoelectric-photovoltaic hybrid systems based on wide-gap solar cells
The model results showed in all three cases efficiency gains with a maximum of +3. 1% for Perovskites (from 16. 4% to 19. 5%).
Applied Physics
Neural Machine Translation: A Review of Methods, Resources, and Tools
Machine translation (MT) is an important sub-field of natural language processing that aims to translate natural languages using computers.
Towards a Universal Continuous Knowledge Base
In this work, we propose a method for building a continuous knowledge base (CKB) that can store knowledge imported from multiple, diverse neural networks.
Writing and deleting skyrmions with electric fields in a multiferroic heterostructure
Magnetic skyrmions are topological spin textures that can be used as information carriers for the next-generation information storage and processing.
Strongly Correlated Electrons Mesoscale and Nanoscale Physics Materials Science
Learning Symbolic Expressions via Gumbel-Max Equation Learner Networks
Most of the neural networks (NNs) learned via state-of-the-art machine learning techniques are black-box models.
LINDT: Tackling Negative Federated Learning with Local Adaptation
On occasion of NFL recovery, the framework makes adaptation to the federated model on each client's local data by learning a Layer-wise Intertwined Dual-model.
Field-Tuned Quantum Effects in a Triangular-Lattice Ising Magnet
We report thermodynamic and neutron scattering measurements of the triangular-lattice quantum Ising magnet TmMgGaO 4 in longitudinal magnetic fields.
Strongly Correlated Electrons Materials Science
BERT-JAM: Boosting BERT-Enhanced Neural Machine Translation with Joint Attention
In this work, we propose a novel BERT-enhanced NMT model called BERT-JAM which improves upon existing models from two aspects: 1) BERT-JAM uses joint-attention modules to allow the encoder/decoder layers to dynamically allocate attention between different representations, and 2) BERT-JAM allows the encoder/decoder layers to make use of BERT's intermediate representations by composing them using a gated linear unit (GLU).
MLCask: Efficient Management of Component Evolution in Collaborative Data Analytics Pipelines
In this paper, we identify two main challenges that arise during the deployment of machine learning pipelines, and address them with the design of versioning for an end-to-end analytics system MLCask.
Privacy Preserving Vertical Federated Learning for Tree-based Models
Federated learning (FL) is an emerging paradigm that enables multiple organizations to jointly train a model without revealing their private data to each other.
Planimation
Planimation is a modular and extensible open source framework to visualise sequential solutions of planning problems specified in PDDL.
Higher-order topological semimetal in acoustic crystals
Here we report the realization of a second-order topological Weyl semimetal in a 3D-printed acoustic crystal, which possesses Weyl points in 3D momentum space, 2D Fermi arc states on surfaces and 1D gapless states on hinges.
Mesoscale and Nanoscale Physics
Pyramid: A Layered Model for Nested Named Entity Recognition
Its hidden state at layer l represents an l-gram in the input text, which is labeled only if its corresponding text region represents a complete entity mention.
Ranked #1 on
Nested Named Entity Recognition
on NNE
Robust Federated Recommendation System
We argue that the key to Byzantine detection is monitoring of gradients of the model parameters of clients.
Decorrelated Double Q-learning
Q-learning with value function approximation may have the poor performance because of overestimation bias and imprecise estimate.
A Transactional Perspective on Execute-order-validate Blockchains
For evaluation, we implement our method in two blockchains respectively, FabricSharp on top of Hyperledger Fabric, and FastFabricSharp on top of FastFabric.
Distributed, Parallel, and Cluster Computing Databases Performance
Analysis of Indexing Structures for Immutable Data
We establish the worst-case guarantees of each index in terms of these five metrics, and we experimentally evaluate all indexes in a large variety of settings.
Databases
The Alzheimer's Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge: Results after 1 Year Follow-up
TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease.
ISBNet: Instance-aware Selective Branching Networks
Recent years have witnessed growing interests in designing efficient neural networks and neural architecture search (NAS).
PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phones
Over the last years, a great success of deep neural networks (DNNs) has been witnessed in computer vision and other fields.
Learning to Predict Explainable Plots for Neural Story Generation
While the use of neural networks has proven effective in improving story generation, how to learn to generate an explainable high-level plot still remains a major challenge.
Merging Deterministic Policy Gradient Estimations with Varied Bias-Variance Tradeoff for Effective Deep Reinforcement Learning
Deep reinforcement learning (DRL) on Markov decision processes (MDPs) with continuous action spaces is often approached by directly training parametric policies along the direction of estimated policy gradients (PGs).
Context-aware Active Multi-Step Reinforcement Learning
Then given the selected samples, we propose the adaptive multi-step TD, which generalizes TD($\lambda$), but adaptively switch on/off the backups from future returns of different steps.
Stain Style Transfer using Transitive Adversarial Networks
It is not necessary for an expert to pick a representative reference slide in the proposed TAN method.
A New Framework for Multi-Agent Reinforcement Learning -- Centralized Training and Exploration with Decentralized Execution via Policy Distillation
Guided by this framework and the maximum-entropy learning technique, we will first train agents' policies with shared global component to foster coordinated and effective learning.
Learning to Navigate from Simulation via Spatial and Semantic Information Synthesis with Noise Model Embedding
While training an end-to-end navigation network in the real world is usually of high cost, simulation provides a safe and cheap environment in this training stage.
Blockchains vs. Distributed Databases: Dichotomy and Fusion
As blockchain evolves into another data management system, the natural question is how it compares against distributed database systems.
Databases Performance
The Disruptions of 5G on Data-driven Technologies and Applications
With 5G on the verge of being adopted as the next mobile network, there is a need to analyze its impact on the landscape of computing and data management.
Networking and Internet Architecture Databases Distributed, Parallel, and Cluster Computing
Database Meets Deep Learning: Challenges and Opportunities
Deep learning has recently become very popular on account of its incredible success in many complex data-driven applications, such as image classification and speech recognition.
Memetic EDA-Based Approaches to Comprehensive Quality-Aware Automated Semantic Web Service Composition
The objective of this problem is to find a solution with optimized or near-optimized overall QoS and QoSM within polynomial time over a service request.
Blockchain Goes Green? An Analysis of Blockchain on Low-Power Nodes
Motivated by the massive energy usage of blockchain, on the one hand, and by significant performance improvements in low-power, wimpy systems, on the other hand, we perform an in-depth time-energy analysis of blockchain systems on low-power nodes in comparison to high-performance nodes.
Distributed, Parallel, and Cluster Computing Databases Emerging Technologies Performance
Effective and Efficient Dropout for Deep Convolutional Neural Networks
However, many recent works show that the standard dropout is ineffective or even detrimental to the training of CNNs.
Model Slicing for Supporting Complex Analytics with Elastic Inference Cost and Resource Constraints
Model slicing could be viewed as an elastic computation solution without requiring more computational resources.
Evolutionary Multitasking for Semantic Web Service Composition
We also found that the use of the proper neighborhood structure can enhance the effectiveness of our approach.
Off-Policy Actor-Critic in an Ensemble: Achieving Maximum General Entropy and Effective Environment Exploration in Deep Reinforcement Learning
We propose a new policy iteration theory as an important extension of soft policy iteration and Soft Actor-Critic (SAC), one of the most efficient model free algorithms for deep reinforcement learning.
Optimizing Controller Placement for Software-Defined Networks
In comparison to communication delay, existing literature on the CPP assumes that the influence of controller workload distribution on network performance is negligible.
Composing Distributed Data-intensive Web Services Using a Flexible Memetic Algorithm
Data-intensive Web services, which manipulate and deal with those data, are of great interest to implement data-intensive processes, such as distributed Data-intensive Web Service Composition (DWSC).
Distance-Guided GA-Based Approach to Distributed Data-Intensive Web Service Composition
As a fundamental challenge for service developers, service composition must fulfil functional requirements and optimise Quality of Service (QoS) attributes, simultaneously.
Effective Exploration for Deep Reinforcement Learning via Bootstrapped Q-Ensembles under Tsallis Entropy Regularization
With the aim of improving sample efficiency and learning performance, we will develop a new DRL algorithm in this paper that seamless integrates entropy-induced and bootstrap-induced techniques for efficient and deep exploration of the learning environment.
PANDA: Facilitating Usable AI Development
In many complex applications such as healthcare, subject matter experts (e. g. Clinicians) are the ones who appreciate the importance of features that affect health, and their knowledge together with existing knowledge bases are critical to the end results.
An Adaptive Clipping Approach for Proximal Policy Optimization
While PPO is inspired by the same learning theory that justifies trust region policy optimization (TRPO), PPO substantially simplifies algorithm design and improves data efficiency by performing multiple epochs of \emph{clipped policy optimization} from sampled data.
Rafiki: Machine Learning as an Analytics Service System
Second, expertise knowledge is required to optimize the training and inference procedures in terms of efficiency and effectiveness, which imposes heavy burden on the system users.
ForkBase: An Efficient Storage Engine for Blockchain and Forkable Applications
By integrating the core application properties into the storage, ForkBase not only delivers high performance but also reduces development effort.
Databases Cryptography and Security Distributed, Parallel, and Cluster Computing
A Roadmap for HEP Software and Computing R&D for the 2020s
Particle physics has an ambitious and broad experimental programme for the coming decades.
Computational Physics High Energy Physics - Experiment
Untangling Blockchain: A Data Processing View of Blockchain Systems
Blockchain technologies are gaining massive momentum in the last few years.
Databases Cryptography and Security
BLOCKBENCH: A Framework for Analyzing Private Blockchains
However, there is a clear lack of a systematic framework with which different systems can be analyzed and compared against each other.
Databases Cryptography and Security Distributed, Parallel, and Cluster Computing
Joint Visual Denoising and Classification using Deep Learning
Our model is a 3-pathway deep architecture with a hidden-layer representation which is shared by multi-inputs and outputs, and each branch can be composed of a multi-layer deep model.
Word Recognition with Deep Conditional Random Fields
On the other hand, word recognition is a sequential problem where we need to model the correlation between characters.
A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation
We describe recurrent neural networks (RNNs), which have attracted great attention on sequential tasks, such as handwriting recognition, speech recognition and image to text.
Deep Learning At Scale and At Ease
The other is scalability, that is the deep learning system must be able to provision for a huge demand of computing resources for training large models with massive datasets.
A Light Sliding-Window Part-of-Speech Tagger for the Apertium Free/Open-Source Machine Translation Platform
This paper describes a free/open-source implementation of the light sliding-window (LSW) part-of-speech tagger for the Apertium free/open-source machine translation platform.
Generalized K-fan Multimodal Deep Model with Shared Representations
In this paper, we propose a K-fan deep structure model, which can handle the multi-input and muti-output learning problems effectively.
Deep Transductive Semi-supervised Maximum Margin Clustering
Thus, our model unifies transductive learning, feature learning and maximum margin techniques in the semi-supervised clustering framework.
Deep Learning with Nonparametric Clustering
As an unsupervised method, our model first leverages the advantages of deep learning for feature representation and dimension reduction.
Sequential Labeling with online Deep Learning
Deep learning has attracted great attention recently and yielded the state of the art performance in dimension reduction and classification problems.
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.
Restricted Boltzmann Machine for Classification with Hierarchical Correlated Prior
We propose a hierarchical correlated RBM for classification problem, which generalizes the classification RBM with sharing information among different classes.
Latent Fisher Discriminant Analysis
In this paper, we overcome this limitation and propose a latent variable Fisher discriminant analysis model.
