Liang Chen

A Covert Channel Over VoLTE via Adjusting Silence Periods

2018 · IEEE Access

Covert channels represent unforeseen communication methods that exploit authorized overt communication as the carrier medium for covert messages. Covert channels can be a secure and effective means of transmitting confidential information hidden in overt traffic. …

Memory Augmented Policy Optimization for Program Synthesis with Generalization

2018 · arXiv (Cornell University)

This paper presents Memory Augmented Policy Optimization (MAPO): a novel policy optimization formulation that incorporates a memory buffer of promising trajectories to reduce the variance of policy gradient estimates for deterministic environments with discrete actions. …

Variance-reduced Language Pretraining via a Mask Proposal Network

2020 · arXiv (Cornell University)

Self-supervised learning, a.k.a., pretraining, is important in natural language processing. Most of the pretraining methods first randomly mask some positions in a sentence and then train a model to recover the tokens at the masked …

Auth+Track: Enabling Authentication Free Interaction on Smartphone by Continuous User Tracking

2021

We propose Auth+Track, a novel authentication model that aims to reduce redundant authentication in everyday smartphone usage. By sparse authentication and continuous tracking of the user’s status, Auth+Track eliminates the “gap” authentication between fragmented sessions …

ARCH: Efficient Adversarial Regularized Training with Caching

2021

Adversarial regularization can improve model generalization in many natural language processing tasks. However, conventional approaches are computationally expensive since they need to generate a perturbation for each sample in each epoch. We propose a new …

Token-wise Curriculum Learning for Neural Machine Translation

2021 · arXiv (Cornell University)

Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. This is not always achievable for low-resource languages where the amount …

Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attack

2022 · arXiv (Cornell University)

Deep graph learning (DGL) has achieved remarkable progress in both business and scientific areas ranging from finance and e-commerce to drug and advanced material discovery. Despite the progress, applying DGL to real-world applications faces a …

Neighboring Backdoor Attacks on Graph Convolutional Network

2022 · arXiv (Cornell University)

Backdoor attacks have been widely studied to hide the misclassification rules in the normal models, which are only activated when the model is aware of the specific inputs (i.e., the trigger). However, despite their success …

Mutual Nearest Neighbor Contrast and Hybrid Prototype Self-Training for Universal Domain Adaptation

2022 · Proceedings of the AAAI Conference on Artificial Intelligence

Universal domain adaptation (UniDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled target domain under domain shift and category shift. Without prior category overlap information, it is challenging to simultaneously …

CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing

2022 · arXiv (Cornell University)

Model ensemble is a popular approach to produce a low-variance and well-generalized model. However, it induces large memory and inference costs, which are often not affordable for real-world deployment. Existing work has resorted to sharing …

Astrophysically sourced quantum coherent photonic signals

2023 · Physical review. D/Physical review. D.

Stimulated emission is shown to be robust in stars. Through Bose enhancement this produces quantum states of aligned, monochromatic photons somewhat similar to a laser. The probability of creating such states is computed. We show …

NRPP: A Learning Graph Representation Approach for Network Robustness Prediction

2024

In the field of modern network science, robustness is a key factor in evaluating the characteristics of complex networks. Connectivity robustness and controllability robustness are two important measures. They refer to a network's ability to …

Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

2017

Harnessing the statistical power of neural networks to perform language understanding and symbolic reasoning is difficult, when it requires executing efficient discrete operations against a large knowledge-base. In this work, we introduce a Neural Symbolic …

Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

2016 · arXiv (Cornell University)

Harnessing the statistical power of neural networks to perform language understanding and symbolic reasoning is difficult, when it requires executing efficient discrete operations against a large knowledge-base. In this work, we introduce a Neural Symbolic …

Self-supervised Graph Learning for Recommendation

2021

Representation learning on user-item graph for recommendation has evolved from using single ID or interaction history to exploiting higher-order neighbors. This leads to the success of graph convolution networks (GCNs) for recommendation such as PinSage …

AutoDebias: Learning to Debias for Recommendation

2021

Recommender systems rely on user behavior data like ratings and clicks to build personalization model. However, the collected data is observational rather than experimental, causing various biases in the data which significantly affect the learned …