Search Results for author:
Found 34 papers, 10 papers with code
Life-Cycle Emissions of AI Hardware: A Cradle-To-Grave Approach and Generational Trends
Specialized hardware accelerators aid the rapid advancement of artificial intelligence (AI), and their efficiency impacts AI's environmental sustainability.
Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker
To make more effective use of supplementary demonstrations, we introduce meta-goal in ILMAR to optimize the functional of the advantage function by explicitly minimizing the distance between the current policy and the expert policy.
Temporal Action Localization with Cross Layer Task Decoupling and Refinement
Temporal action localization (TAL) involves dual tasks to classify and localize actions within untrimmed videos.
ADSNet: Cross-Domain LTV Prediction with an Adaptive Siamese Network in Advertising
We introduce a gain evaluation strategy to calculate information gain, aiding the model in learning helpful information for the target domain and providing the ability to reject noisy samples, thus avoiding negative transfer.
A Novel Paradigm in Solving Multiscale Problems
By enabling the acquisition of large-scale data with minimal computational demands, coupled with the efficient and accurate characterization of small-scale dynamics via Spectral PINN, our approach offers a valuable and promising approach for researchers seeking to tackle multiscale phenomena effectively.
An Incentive Mechanism for Federated Learning Based on Multiple Resource Exchange
We formulate the interaction between MO and DOs as an optimization problem, and the objective is to effectively utilize the communication and computing resource of the MO and DOs to minimize the time to complete an FL task.
SHAPE: A Sample-adaptive Hierarchical Prediction Network for Medication Recommendation
Effectively medication recommendation with complex multimorbidity conditions is a critical task in healthcare.
Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation
To this end, we investigate the limits of historical information for temporal knowledge graph extrapolation and propose a new event forecasting model called Contrastive Event Network (CENET) based on a novel training framework of historical contrastive learning.
Physics-Assisted Reduced-Order Modeling for Identifying Dominant Features of Transonic Buffet
The dominant latent space further reveals a strong relevance with the key flow features located in the boundary layers downstream of shock.
Segmentation, Classification, and Quality Assessment of UW-OCTA Images for the Diagnosis of Diabetic Retinopathy
Diabetic Retinopathy (DR) is a severe complication of diabetes that can cause blindness.
Temporal Knowledge Graph Reasoning with Historical Contrastive Learning
Simultaneously, it trains representations of queries to investigate whether the current moment depends more on historical or non-historical events by launching contrastive learning.
Joint nnU-Net and Radiomics Approaches for Segmentation and Prognosis of Head and Neck Cancers with PET/CT images
Then 3D nnU-Net architecture was adopted to automatic segmentation of primary tumor and lymph nodes synchronously. Based on predicted segmentation, ten conventional features and 346 standardized radiomics features were extracted for each patient.
Automatic Check-Out via Prototype-based Classifier Learning from Single-Product Exemplars
Automatic Check-Out (ACO) aims to accurately predict the presence and count of each category of products in check-out images, where a major challenge is the significant domain gap between training data (single-product exemplars) and test data (check-out images).
KnowledgeShovel: An AI-in-the-Loop Document Annotation System for Scientific Knowledge Base Construction
Constructing a comprehensive, accurate, and useful scientific knowledge base is crucial for human researchers synthesizing scientific knowledge and for enabling Al-driven scientific discovery.
CATNet: Cross-event Attention-based Time-aware Network for Medical Event Prediction
It is a time-aware, event-aware and task-adaptive method with the following advantages: 1) modeling heterogeneous information and temporal information in a unified way and considering temporal irregular characteristics locally and globally respectively, 2) taking full advantage of correlations among different types of events via cross-event attention.
Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations
Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a so-called Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues.
A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection
In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset.
DeepShovel: An Online Collaborative Platform for Data Extraction in Geoscience Literature with AI Assistance
Geoscientists, as well as researchers in many fields, need to read a huge amount of literature to locate, extract, and aggregate relevant results and data to enable future research or to build a scientific database, but there is no existing system to support this use case well.
The China Trade Shock and the ESG Performances of US firms
Exploiting a trade policy in which US congress granted China the Permanent Normal Trade Relations and the resulting change in expected tariff rates on Chinese imports, we find that greater import competition from China leads to an increase in the US company's ESG performance.
Multimodal data matters: language model pre-training over structured and unstructured electronic health records
As two important textual modalities in electronic health records (EHR), both structured data (clinical codes) and unstructured data (clinical narratives) have recently been increasingly applied to the healthcare domain.
DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration
One of the main challenges of transferring the policy learned in a simulated environment to real world, is the discrepancy between the dynamics of the two environments.
Robotics
Turbulence suppression by streamwise-varying wall rotation in pipe flow
Two control parameters, which are velocity amplitude and wavelength, are considered.
Fluid Dynamics
Deep Learning in the Era of Edge Computing: Challenges and Opportunities
The era of edge computing has arrived.
High-Order Relation Construction and Mining for Graph Matching
Iterated line graphs are introduced for the first time to describe such high-order information, based on which we present a new graph matching method, called High-order Graph Matching Network (HGMN), to learn not only the local structural correspondence, but also the hyperedge relations across graphs.
GPRInvNet: Deep Learning-Based Ground Penetrating Radar Data Inversion for Tunnel Lining
The results have demonstrated that the GPRInvNet is capable of effectively reconstructing complex tunnel lining defects with clear boundaries.
Regression via Arbitrary Quantile Modeling
In the regression problem, L1 and L2 are the most commonly used loss functions, which produce mean predictions with different biases.
Detecting Deep Neural Network Defects with Data Flow Analysis
Deep neural networks (DNNs) are shown to be promising solutions in many challenging artificial intelligence tasks.
HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking
Without the constraint imposed by the hand-designed heuristics, our searched networks contain more flexible and meaningful architectures that existing weight sharing based NAS approaches are not able to discover.
Strongly Independent Matrices and Rigidity of $\times A$-Invariant Measures on $n$-Torus
We introduce the concept of strongly independent matrices over any field, and prove the existence of such matrices for certain fields and the non-existence for algebraically closed fields.
Dynamical Systems 37A05, 37A25, 37A46, 43A05, 28C10, 12E05
Nektar++: enhancing the capability and application of high-fidelity spectral/$hp$ element methods
Nektar++ is an open-source framework that provides a flexible, high-performance and scalable platform for the development of solvers for partial differential equations using the high-order spectral/$hp$ element method.
Mathematical Software Numerical Analysis Numerical Analysis Fluid Dynamics
DeepObfuscation: Securing the Structure of Convolutional Neural Networks via Knowledge Distillation
Our obfuscation approach is very effective to protect the critical structure of a deep learning model from being exposed to attackers.
Cryptography and Security
On Secure and Usable Program Obfuscation: A Survey
On the other hand, the performance requirement for model-oriented obfuscation approaches is too weak to develop practical program obfuscation solutions.
Cryptography and Security Software Engineering
N-Version Obfuscation: Impeding Software Tampering Replication with Program Diversity
Our idea is to impede the replication of tampering via program diversification, and thus increasing the complexity to break the whole software system.
Cryptography and Security Programming Languages
Convolution and convolution-root properties of long-tailed distributions
These examples help to provide further insights and, in particular, to show that the properties to be both long-tailed and so-called "generalised subexponential" are not preserved under the convolution roots.
Probability 60E05, 60F10, 60G50
