Search Results for author:
Found 12 papers, 4 papers with code
Building Flexible Machine Learning Models for Scientific Computing at Scale
Foundation models have revolutionized knowledge acquisition across domains, and our study introduces OmniArch, a paradigm-shifting approach designed for building foundation models in multi-physics scientific computing.
PhoGAD: Graph-based Anomaly Behavior Detection with Persistent Homology Optimization
The analysis of persistent homology demonstrates its effectiveness in capturing the topological structure formed by normal edge features.
Learning Music Sequence Representation from Text Supervision
Music representation learning is notoriously difficult for its complex human-related concepts contained in the sequence of numerical signals.
Task-Specific Expert Pruning for Sparse Mixture-of-Experts
The sparse Mixture-of-Experts (MoE) model is powerful for large-scale pre-training and has achieved promising results due to its model capacity.
THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption
As more and more pre-trained language models adopt on-cloud deployment, the privacy issues grow quickly, mainly for the exposure of plain-text user data (e. g., search history, medical record, bank account).
MTTrans: Cross-Domain Object Detection with Mean-Teacher Transformer
To solve this problem, we propose an end-to-end cross-domain detection Transformer based on the mean teacher framework, MTTrans, which can fully exploit unlabeled target domain data in object detection training and transfer knowledge between domains via pseudo labels.
POLLA: Enhancing the Local Structure Awareness in Long Sequence Spatial-temporal Modeling
Extensive experiments are conducted on five large-scale datasets, which demonstrate that our method achieves state-of-the-art performance and validates the effectiveness brought by local structure information.
Gradient Broadcast Adaptation: Defending against the backdoor attack in pre-trained models
Pre-trained language models (e. g, BERT, GPT-3) have revolutionized the NLP research and fine-tuning becomes the indispensable step of downstream adaptation.
RoSearch: Search for Robust Student Architectures When Distilling Pre-trained Language Models
In order to overcome these security problems, RoSearch is proposed as a comprehensive framework to search the student models with better adversarial robustness when performing knowledge distillation.
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Many real-world applications require the prediction of long sequence time-series, such as electricity consumption planning.
Ranked #1 on
Time Series Forecasting
on ETTh2 (336) Univariate
Differentially-private Federated Neural Architecture Search
To address this problem, we propose federated neural architecture search (FNAS), where different parties collectively search for a differentiable architecture by exchanging gradients of architecture variables without exposing their data to other parties.
Stacked Kernel Network
Similar to DNNs, a SKN is composed of multiple layers of hidden units, but each parameterized by a RKHS function rather than a finite-dimensional vector.
