Ke Wang

SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks

2018

Generating texts of different sentiment labels is getting more and more attention in the area of natural language generation. Recently, Generative Adversarial Net (GAN) has shown promising results in text generation. However, the texts generated …

Secure Top-k Inner Product Retrieval

2018

Secure top-k inner product retrieval allows the users to outsource encrypted data vectors to a cloud server and at some later time find the k vectors producing largest inner products giving an encrypted query vector. …

Learning a Static Bug Finder from Data

2019 · arXiv (Cornell University)

We present an alternative approach to creating static bug finders. Instead of relying on human expertise, we utilize deep neural networks to train static analyzers directly from data. In particular, we frame the problem of …

Testing Neural Programs.

2019 · arXiv (Cornell University)

Deep neural networks have been increasingly used in software engineering and program analysis tasks. They usually take a program and make some predictions about it, e.g., bug prediction. We call these models neural program analyzers. …

Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation

2019 · arXiv (Cornell University)

Unsupervised text attribute transfer automatically transforms a text to alter a specific attribute (e.g. sentiment) without using any parallel data, while simultaneously preserving its attribute-independent content. The dominant approaches are trying to model the content-independent …

Safety evaluation and risk reasoning of metro station based on IFPN

2019 · IOP Conference Series Materials Science and Engineering

Abstract In order to realize the accurate evaluation of the safety status of metro station and the high-efficiency identification of the risk cause, an improved fuzzy petri net is introduced to describe the safety risk …

Assessing the Fairness of Classifiers with Collider Bias.

2020 · arXiv (Cornell University)

The increasing maturity of machine learning technologies and their applications to decisions relate to everyday decision making have brought concerns about the fairness of the decisions. However, current fairness assessment systems often suffer from collider …

An Improved BP Neural Network-based Quality Evaluation Model for Chinese International Education Teaching Courses

2022

For learners of Chinese as a second language, it is difficult to learn Chinese in the target language environment. With the large-scale applications of intelligent technology in Chinese international education, Chinese teaching is moving towards …

Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting and Regularization

2020 · arXiv (Cornell University)

Deep neural networks generalize well despite being exceedingly overparameterized and being trained without explicit regularization. This curious phenomenon has inspired extensive research activity in establishing its statistical principles: Under what conditions is it observed? How …

Multi-axis Gating MLP with Bidirectional Feature Extraction for Sequence Recommendation

2022 · 2022 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech)

The sequence recommendation task uses neural network models such as GRU and Self-Attention to extract potential preference characteristics from the user’s behavior data, This makes the recommendation more accurate. However, they use the sequence information …

ChainDB: Ensuring Integrity of Querying Off-Chain Data on Blockchain

2022

Enterprise blockchain applications have been widely adopted and the data scale on blockchain increases rapidly in recent years. In practical application, participants prefer to store most of the business data in local database systems and …

Non-parametric, Nearest-neighbor-assisted Fine-tuning for Neural Machine Translation

2023 · arXiv (Cornell University)

Non-parametric, k-nearest-neighbor algorithms have recently made inroads to assist generative models such as language models and machine translation decoders. We explore whether such non-parametric models can improve machine translation models at the fine-tuning stage by …

Computing SHAP Efficiently Using Model Structure Information

2023 · arXiv (Cornell University)

SHAP (SHapley Additive exPlanations) has become a popular method to attribute the prediction of a machine learning model on an input to its features. One main challenge of SHAP is the computation time. An exact …

A Quantum Automatic Tool for Finding Impossible Differentials

2024 · arXiv (Cornell University)

Due to the superiority of quantum computing, traditional cryptography is facing severe threat. This makes the security evaluation of cryptographic systems in quantum attack models significant and urgent. For symmetric ciphers, the security analysis heavily …

Dynamic Multimodal Prompt Deep Collaboration Strategy For Classification and Question-Answering Problem in Industrial Training

2025

Traditional training methods involve learning through books or e-books, followed by practical training, which is inefficient. To address the issue of low efficiency in traditional training methods, this paper proposes an innovative industrial training approach …

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis

2025 · arXiv (Cornell University)

Inductive program synthesis, or programming by example, requires synthesizing functions from input-output examples that generalize to unseen inputs. While large language model agents have shown promise in programming tasks guided by natural language, their ability …

Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding

2018

Top-N sequential recommendation models each user as a sequence of items interacted in the past and aims to predict top-N ranked items that a user will likely interact in a »near future». The order of …