Weiping Wang

Attention-Based Relation Extraction With Bidirectional Gated Recurrent Unit and Highway Network in the Analysis of Geological Data

2017 · IEEE Access

Attention-based deep learning model as a human-centered smart technology has become the state-of-the-art method in addressing relation extraction, while implementing natural language processing. How to effectively improve the computational performance of that model has always …

Learning Vector-valued Functions with Local Rademacher Complexity and Unlabeled Data

2019 · arXiv (Cornell University)

We consider a general family of problems of which the output space admits vector-valued structure, covering a broad family of important domains, e.g. multi-label learning and multi-class classification. By using local Rademacher complexity and unlabeled …

OMOPredictor: An Online Multi-Step Operator Performance Prediction Framework in Distributed Streaming Processing

2019

Recently, with the development of distributed stream processing systems, the elastic resource scaling technique has been significantly improved. Many researchers focus on leveraging the approaches based on predicting the trend of data load to implement …

Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation

2021 · arXiv (Cornell University)

Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teacher's soft label as in conventional KD, researchers find that the rich information contained in the hidden layers …

FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

Recent Newton-type federated learning algorithms have demonstrated linear convergence with respect to the communication rounds. However, communicating Hessian matrices is often unfeasible due to their quadratic communication complexity. In this paper, we introduce a novel …

Key-Point-Driven Mathematical Reasoning Distillation of Large Language Model

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have demonstrated exceptional proficiency in mathematical reasoning tasks due to their extensive parameter counts and training on vast datasets. Despite these capabilities, deploying LLMs is hindered by their computational demands. Distilling …

Efficient shortest distance approximate query on large scale encrypted graph data

2025 · Cybersecurity

Abstract The problem of querying shortest distance on a graph has attracted significant research attention due to the widespread applicability of graphs and the ability of graph shortest path queries to address numerous application problems. …