Jie Yang

Hierarchical Label Propagation and Discovery for Machine Generated Email

2016

Machine-generated documents such as email or dynamic web pages are single instantiations of a pre-defined structural template. As such, they can be viewed as a hierarchy of template and document specific content. This hierarchical template …

Design Challenges and Misconceptions in Neural Sequence Labeling

2018 · International Conference on Computational Linguistics

We investigate the design challenges of constructing effective and efficient neural sequence labeling systems, by reproducing twelve neural sequence labeling models, which include most of the state-of-the-art structures, and conduct a systematic model comparison on …

A Double-Variational Bayesian Framework in Random Fourier Features for Indefinite Kernels

2019 · IEEE Transactions on Neural Networks and Learning Systems

Random Fourier features (RFFs) have been successfully employed to kernel approximation in large-scale situations. The rationale behind RFF relies on Bochner's theorem, but the condition is too strict and excludes many widely used kernels, e.g., …

Seeing the wood for the trees: Insights into the complexity of developing pre-service teachers’ digital competencies for future teaching

2019 · ASCILITE Publications

Developing digital competencies is a critical component in pre-service teacher training for future practice. However, this is a complex process which includes a range of strategies, and little is known about how they should be …

Are We Evaluating Rigorously? Benchmarking Recommendation for Reproducible Evaluation and Fair Comparison

2020

With tremendous amount of recommendation algorithms proposed every year, one critical issue has attracted a considerable amount of attention: there are no effective benchmarks for evaluation, which leads to two major concerns, i.e., unreproducible evaluation …

Security and Operational considerations for manufacturer installed keys and anchors

2020

This document provides a nomenclature to describe ways in which manufacturers secure private keys and public trust anchors in devices. RFCEDITOR: please remove this paragraph. This work is occuring in https://github.com/mcr/idevid-security-considerations

DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation

2020 · arXiv (Cornell University)

Automatic detecting anomalous regions in images of objects or textures without priors of the anomalies is challenging, especially when the anomalies appear in very small areas of the images, making difficult-to-detect visual variations, such as …

Residual Enhanced Multi-Hypergraph Neural Network

2021

Hypergraphs are a generalized data structure of graphs to model higher-order correlations among entities, which have been successfully adopted into various researching fields. Meanwhile, HyperGraph Neural Network (HGNN) is currently the de-facto method for hypergraph …

Towards Fine-grained Causal Reasoning and QA

2022 · arXiv (Cornell University)

Understanding causality is key to the success of NLP applications, especially in high-stakes domains. Causality comes in various perspectives such as enable and prevent that, despite their importance, have been largely ignored in the literature. …

FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning

2022 · arXiv (Cornell University)

Recently, webly supervised learning (WSL) has been studied to leverage numerous and accessible data from the Internet. Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by …

[MASK] Insertion: a robust method for anti-adversarial attacks

2023

Adversarial attack aims to perturb input sequences and mislead a trained model for false predictions. To enhance the model robustness, defensing methods are accordingly employed by either data augmentation (involving adversarial samples) or model enhancement …

Multi-Augmentation-Based Contrastive Learning for Semi-Supervised Learning

2024 · Algorithms

Semi-supervised learning has been proven to be effective in utilizing unlabeled samples to mitigate the problem of limited labeled data. Traditional semi-supervised learning methods generate pseudo-labels for unlabeled samples and train the classifier using both …

Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection

2024 · arXiv (Cornell University)

Graph-based anomaly detection is currently an important research topic in the field of graph neural networks (GNNs). We find that in graph anomaly detection, the homophily distribution differences between different classes are significantly greater than …

NeuroSORT: A Neuromorphic Accelerator for Spike-based Online and Real-time Tracking

2024

The increasing need for real-time computation with low-power consumption is driving the advancement of specialized neuromorphic processors on various applications. Multi object tracking, as one of the most challenging tasks in computer vision, has gained …

Integrated high-performance LDPC decoder for Continuous-Variable Quantum Key Distribution System

2025

The throughput of the error correction decoding is one of the major bottlenecks of high-speed continuous-variable quantum key distribution (CV-QKD) systems and an integrated decoder with Gbps decoding throughput is implemented in this work.

Towards Robust Synthetic Aperture Radar Classification: Counteracting Black‐Box Adversarial Attacks

2025 · IET Radar Sonar & Navigation

ABSTRACT Synthetic Aperture Radar (SAR) image classification using deep neural networks (DNNs) has demonstrated vulnerability to adversarial attacks, particularly black‐box attacks, which rely solely on model output scores to craft effective perturbations. Despite their practical …

X-PRINT:Platform-Agnostic and Scalable Fine-Grained Encrypted Traffic Fingerprinting

2025 · arXiv (Cornell University)

Although encryption protocols such as TLS are widely de-ployed,side-channel metadata in encrypted traffic still reveals patterns that allow application and behavior inference.How-ever,existing fine-grained fingerprinting approaches face two key limitations:(i)reliance on platform-dependent charac-teristics,which restricts generalization across …

<tt>SemAder</tt> : Evading LLM-Based Binary Code Analysis via Structure-Semantics Joint Induction

2026 · ACM Transactions on Privacy and Security

With the rapid advancement of artificial intelligence (AI), particularly the widespread adoption of large language models (LLMs) in code comprehension and analysis, their strong semantic parsing capabilities have introduced new threats to software security. Attackers …

Attention-based Recurrent Convolutional Neural Network for Automatic Essay Scoring

2017

Neural network models have recently been applied to the task of automatic essay scoring, giving promising results. Existing work used recurrent neural networks and convolutional neural networks to model input essays, giving grades based on …

Recurrent knowledge graph embedding for effective recommendation

2018

Knowledge graphs (KGs) have proven to be effective to improve recommendation. Existing methods mainly rely on hand-engineered features from KGs (e.g., meta paths), which requires domain knowledge. This paper presents RKGE, a KG embedding approach …

Chinese NER Using Lattice LSTM

2018

We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon. Compared with character-based methods, our model explicitly leverages word …

Neural Word Segmentation with Rich Pretraining

2017

Neural word segmentation research has benefited from large-scale raw texts by leveraging them for pretraining character and word embeddings. On the other hand, statistical segmentation research has exploited richer sources of external information, such as …