Hao Chen

Chinese Questions Classification in the Law Domain

2017

Question classification is an essential part of Question Answering system(QA). This paper introduces our research work on automatic question classification that depends on the sample set including questions from legal forum. We propose a taxonomy …

Change-point detection for multivariate and non-Euclidean data with local dependency

2019 · arXiv (Cornell University)

In a sequence of multivariate observations or non-Euclidean data objects, such as networks, local dependence is common and could lead to false change-point discoveries. We propose a new way of permutation -- circular block permutation …

Simple Encrypted Arithmetic Library - SEAL v2.1.

2017 · IACR Cryptology ePrint Archive

Achieving fully homomorphic encryption was a longstanding open problem in cryptography until it was resolved by Gentry in 2009. Soon after, several homomorphic encryption schemes were proposed. The early homomorphic encryption schemes were extremely impractical, …

PIR with compressed queries and amortized query processing.

2017 · IACR Cryptology ePrint Archive

Private information retrieval (PIR) is a key building block in many privacy-preserving systems. Unfortunately, existing constructions remain very expensive. This paper introduces two techniques that make the computational variant of PIR (CPIR) more efficient in …

Robust RF Mixture Signal Recognition Using Discriminative Dictionary Learning

2021 · IEEE Access

RF signal recognition is an important element toward RF situational awareness and dynamic spectrum management. In this work, machine learning-based signal recognition algorithms are proposed. Our key contribution is to engineer feature learning such that …

Spectral complexity-scaled generalization bound of complex-valued neural networks

2023 · Edinburgh Research Explorer (University of Edinburgh)

Complex-valued neural networks (CVNNs) have been widely applied in various fields, primarily in signal processing and image recognition. Few studies have focused on the generalisation of CVNNs, although it is vital to ensure the performance …

Predicting the occurrence of venous thromboembolism: construction and verification of Risk Warning Model

2020 · Research Square

Abstract Background: The onset of venous thromboembolism is insidious and the prognosis is poor. In this study, we aimed to construct a VTE risk early warning model and explore the clinical application value of the …

GPatch: Patching Graph Neural Networks for Cold-Start Recommendations

2022 · arXiv (Cornell University)

Cold start is an essential and persistent problem in recommender systems. State-of-the-art solutions rely on training hybrid models for both cold-start and existing users/items, based on the auxiliary information. Such a hybrid model would compromise …

SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning

2023 · arXiv (Cornell University)

The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling …

Improving Adversarial Transferability via Intermediate-level Perturbation Decay

2023 · arXiv (Cornell University)

Intermediate-level attacks that attempt to perturb feature representations following an adversarial direction drastically have shown favorable performance in crafting transferable adversarial examples. Existing methods in this category are normally formulated with two separate stages, where …

Diffusion Models for Imperceptible and Transferable Adversarial Attack

2023 · arXiv (Cornell University)

Many existing adversarial attacks generate $L_p$-norm perturbations on image RGB space. Despite some achievements in transferability and attack success rate, the crafted adversarial examples are easily perceived by human eyes. Towards visual imperceptibility, some recent …

Fine-Grained Alignment for Boundary Samples under Open Set Domain Adaptation

2023

Open set domain adaptation aims to transfer knowledge in the presence of unknown samples in the target domain. Previous approaches use additional classifiers or threshold-based methods to identify unknown samples and try to investigate the …

TAROT: A Hierarchical Framework with Multitask Co-Pretraining on Semi-Structured Data towards Effective Person-Job Fit

2024 · arXiv (Cornell University)

Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation. Recently, pretrained large language models have further enhanced the effectiveness by leveraging richer textual …

Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation

2024 · arXiv (Cornell University)

Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models by weak labels, which is receiving significant attention due to its low annotation cost. Existing approaches focus on generating pseudo labels for supervision while largely ignoring …

Enhancing Explainable Rating Prediction through Annotated Macro Concepts

2024

Generating recommendation reasons for recommendation results is a long-standing problem because it is challenging to explain the underlying reasons for recommending an item based on user and item IDs.Existing models usually learn semantic embeddings for …

Sentiment Analysis of Spanish Political Party Tweets Using Pre-trained Language Models

2024 · arXiv (Cornell University)

Title: Sentiment Analysis of Spanish Political Party Communications on Twitter Using Pre-trained Language Models Authors: Chuqiao Song, Shunzhang Chen, Xinyi Cai, Hao Chen Comments: 21 pages, 6 figures Abstract: This study investigates sentiment patterns within …

Research on movie recommendation algorithm based on graph neural network

2024

In this paper, we present an innovative approach to enhancing the efficacy and personalization of movie recommendation systems by incorporating a Graph Neural Network (GNN) model augmented with an attention mechanism. This model leverages the …

OptiChat: Bridging Optimization Models and Practitioners with Large Language Models

2025 · arXiv (Cornell University)

Optimization models have been applied to solve a wide variety of decision-making problems. These models are usually developed by optimization experts but are used by practitioners without optimization expertise in various application domains. As a …

Self-dual codes and LCD codes in sum-rank metric

2025 · arXiv (Cornell University)

Sum-rank codes are an important class of codes which can be utilized for linear network coding, space-time coding and distributed storage. They can not only reduce the size of network alphabet but also detect and …

Reinforced Lifelong Editing for Language Models

2025 · arXiv (Cornell University)

Large language models (LLMs) acquire information from pre-training corpora, but their stored knowledge can become inaccurate or outdated over time. Model editing addresses this challenge by modifying model parameters without retraining, and prevalent approaches leverage …

Machine Learning-Assisted Design Automation of Integrated Photonic Devices

2025

Photonic inverse design has emerged as a trans-formative approach in the development of integrated photonic devices. The inverse design process primarily relies on two key steps: electromagnetic simulation and optimization algorithms. However, traditional numerical methods …

Noise Label Detection and Correction via Bayesian Weighted Consensus Inference

2026 · Computers

Affected by inter-annotator cognitive differences, fatigue effects, and data poisoning, training data inevitably contains a certain proportion of noise, which severely impairs model performance. Traditional manual verification is costly and inefficient, while existing automatic detection …

A Survey on Evaluation of Large Language Models

2024 · ACM Transactions on Intelligent Systems and Technology

Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, …