Search Results for author: Ling Liu

Found 44 papers, 13 papers with code

IGT2P: From Interlinear Glossed Texts to Paradigms

no code implementations EMNLP 2020 Sarah Moeller, Ling Liu, Changbing Yang, Katharina Kann, Mans Hulden

An intermediate step in the linguistic analysis of an under-documented language is to find and organize inflected forms that are attested in natural speech.


Backtranslation in Neural Morphological Inflection

no code implementations EMNLP (insights) 2021 Ling Liu, Mans Hulden

Backtranslation is a common technique for leveraging unlabeled data in low-resource scenarios in machine translation.

Machine Translation Morphological Inflection +1

Gradient Leakage Attack Resilient Deep Learning

no code implementations25 Dec 2021 Wenqi Wei, Ling Liu

Although deep learning with differential privacy is a defacto standard for publishing deep learning models with differential privacy guarantee, we show that differentially private algorithms with fixed privacy parameters are vulnerable against gradient leakage attacks.

Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering

1 code implementation22 Oct 2021 Zhongwei Xie, Ling Liu, Yanzhao Wu, Luo Zhong, Lin Li

This paper introduces a two-phase deep feature engineering framework for efficient learning of semantics enhanced joint embedding, which clearly separates the deep feature engineering in data preprocessing from training the text-image joint embedding model.

Cross-Modal Retrieval Feature Engineering

Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding

no code implementations14 Oct 2021 Jingya Zhou, Ling Liu, Wenqi Wei, Jianxi Fan

This survey paper reviews the design principles and the different node embedding techniques for network representation learning over homogeneous networks.

Graph Mining Knowledge Graphs +3

Learning Joint Embedding with Modality Alignments for Cross-Modal Retrieval of Recipes and Food Images

no code implementations9 Aug 2021 Zhongwei Xie, Ling Liu, Lin Li, Luo Zhong

This paper presents a three-tier modality alignment approach to learning text-image joint embedding, coined as JEMA, for cross-modal retrieval of cooking recipes and food images.

Cross-Modal Retrieval Term Extraction

Efficient Deep Feature Calibration for Cross-Modal Joint Embedding Learning

no code implementations2 Aug 2021 Zhongwei Xie, Ling Liu, Lin Li, Luo Zhong

This paper introduces a two-phase deep feature calibration framework for efficient learning of semantics enhanced text-image cross-modal joint embedding, which clearly separates the deep feature calibration in data preprocessing from training the joint embedding model.

Feature Engineering

Learning TFIDF Enhanced Joint Embedding for Recipe-Image Cross-Modal Retrieval Service

1 code implementation2 Aug 2021 Zhongwei Xie, Ling Liu, Yanzhao Wu, Lin Li, Luo Zhong

We present a Multi-modal Semantics enhanced Joint Embedding approach (MSJE) for learning a common feature space between the two modalities (text and image), with the ultimate goal of providing high-performance cross-modal retrieval services.

Cross-Modal Retrieval

To POS Tag or Not to POS Tag: The Impact of POS Tags on Morphological Learning in Low-Resource Settings

no code implementations ACL 2021 Sarah Moeller, Ling Liu, Mans Hulden

However, the importance and usefulness of POS tags needs to be examined as NLP expands to low-resource languages because linguists who provide many annotated resources do not place priority on early identification and tagging of POS.


Parallel Detection for Efficient Video Analytics at the Edge

1 code implementation27 Jul 2021 Yanzhao Wu, Ling Liu, Ramana Kompella

A common performance requirement in these mission-critical edge services is the near real-time latency of online object detection on edge devices.

Autonomous Driving Real-Time Object Detection

Gradient-Leakage Resilient Federated Learning

1 code implementation2 Jul 2021 Wenqi Wei, Ling Liu, Yanzhao Wu, Gong Su, Arun Iyengar

This paper presents a gradient leakage resilient approach to privacy-preserving federated learning with per training example-based client differential privacy, coined as Fed-CDP.

Federated Learning

Boosting Ensemble Accuracy by Revisiting Ensemble Diversity Metrics

1 code implementation CVPR 2021 Yanzhao Wu, Ling Liu, Zhongwei Xie, Ka-Ho Chow, Wenqi Wei

Our new metrics significantly improve the intrinsic correlation between high ensemble diversity and high ensemble accuracy.

Ensemble Learning Ensemble Pruning +1

Computational Morphology with Neural Network Approaches

no code implementations19 May 2021 Ling Liu

Neural network approaches have been applied to computational morphology with great success, improving the performance of most tasks by a large margin and providing new perspectives for modeling.

De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks

no code implementations8 May 2021 Jian Chen, Xuxin Zhang, Rui Zhang, Chen Wang, Ling Liu

The results demonstrate that De-Pois is effective and efficient for detecting poisoned data against all the four types of poisoning attacks, with both the accuracy and F1-score over 0. 9 on average.

Data Augmentation Data Poisoning

Deep Ensembles with Hierarchical Diversity Pruning

no code implementations1 Jan 2021 Yanzhao Wu, Ling Liu

(3) We introduce a two phase hierarchical pruning method to effectively identify and prune those deep ensembles with high HQ diversity scores, aiming to increase the lower and upper bounds on ensemble accuracy for the selected ensembles.

Analogy Models for Neural Word Inflection

1 code implementation COLING 2020 Ling Liu, Mans Hulden

Analogy is assumed to be the cognitive mechanism speakers resort to in order to inflect an unknown form of a lexeme based on knowledge of other words in a language.

Utility-Optimized Synthesis of Differentially Private Location Traces

no code implementations14 Sep 2020 Mehmet Emre Gursoy, Vivekanand Rajasekar, Ling Liu

Given a real trace dataset D, the differential privacy parameter epsilon controlling the strength of privacy protection, and the utility/error metric Err of interest; OptaTrace uses Bayesian optimization to optimize DPLTS such that the output error (measured in terms of given metric Err) is minimized while epsilon-differential privacy is satisfied.

Robust Deep Learning Ensemble against Deception

no code implementations14 Sep 2020 Wenqi Wei, Ling Liu

Third, XEnsemble provides a suite of algorithms to combine input verification and output verification to protect the DNN prediction models from both adversarial examples and out of distribution inputs.

Adversarial Robustness Denoising +1

Data Poisoning Attacks Against Federated Learning Systems

2 code implementations16 Jul 2020 Vale Tolpegin, Stacey Truex, Mehmet Emre Gursoy, Ling Liu

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server.

Data Poisoning Federated Learning

Bitcoin Transaction Forecasting with Deep Network Representation Learning

no code implementations15 Jul 2020 Wenqi Wei, Qi Zhang, Ling Liu

First, we explore three interesting properties between Bitcoin transaction accounts: topological connectivity pattern of Bitcoin accounts, transaction amount pattern, and transaction dynamics.

Representation Learning

Understanding Object Detection Through An Adversarial Lens

1 code implementation11 Jul 2020 Ka-Ho Chow, Ling Liu, Mehmet Emre Gursoy, Stacey Truex, Wenqi Wei, Yanzhao Wu

We demonstrate that the proposed framework can serve as a methodical benchmark for analyzing adversarial behaviors and risks in real-time object detection systems.

Adversarial Robustness Autonomous Vehicles +1

Leveraging Principal Parts for Morphological Inflection

no code implementations WS 2020 Ling Liu, Mans Hulden

This paper presents the submission by the CU Ling team from the University of Colorado to SIGMORPHON 2020 shared task 0 on morphological inflection.

Morphological Inflection

LDP-Fed: Federated Learning with Local Differential Privacy

no code implementations5 Jun 2020 Stacey Truex, Ling Liu, Ka-Ho Chow, Mehmet Emre Gursoy, Wenqi Wei

However, in federated learning model parameter updates are collected iteratively from each participant and consist of high dimensional, continuous values with high precision (10s of digits after the decimal point), making existing LDP protocols inapplicable.

Federated Learning

A Framework for Evaluating Gradient Leakage Attacks in Federated Learning

no code implementations22 Apr 2020 Wenqi Wei, Ling Liu, Margaret Loper, Ka-Ho Chow, Mehmet Emre Gursoy, Stacey Truex, Yanzhao Wu

FL offers default client privacy by allowing clients to keep their sensitive data on local devices and to only share local training parameter updates with the federated server.

Federated Learning

A Two stage Adaptive Knowledge Transfer Evolutionary Multi-tasking Based on Population Distribution for Multi/Many-Objective Optimization

no code implementations3 Jan 2020 Zhengping Liang, Weiqi Liang, Xiuju Xu, Ling Liu, Zexuan Zhu

Experimental results on multi-tasking multi-objective optimization test suites show that EMT-PD is superior to other six state-of-the-art evolutionary multi/single-tasking algorithms.

Transfer Learning

Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability

no code implementations21 Nov 2019 Stacey Truex, Ling Liu, Mehmet Emre Gursoy, Wenqi Wei, Lei Yu

Second, through MPLens, we highlight how the vulnerability of pre-trained models under membership inference attack is not uniform across all classes, particularly when the training data itself is skewed.

Inference Attack Membership Inference Attack

Deep Neural Network Ensembles against Deception: Ensemble Diversity, Accuracy and Robustness

no code implementations29 Aug 2019 Ling Liu, Wenqi Wei, Ka-Ho Chow, Margaret Loper, Emre Gursoy, Stacey Truex, Yanzhao Wu

In this paper we first give an overview of the concept of ensemble diversity and examine the three types of ensemble diversity in the context of DNN classifiers.

Ensemble Learning

Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks

no code implementations21 Aug 2019 Ka-Ho Chow, Wenqi Wei, Yanzhao Wu, Ling Liu

Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks.


Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks

1 code implementation18 Aug 2019 Yanzhao Wu, Ling Liu, Juhyun Bae, Ka-Ho Chow, Arun Iyengar, Calton Pu, Wenqi Wei, Lei Yu, Qi Zhang

Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs).

Image Classification

Secure and Utility-Aware Data Collection with Condensed Local Differential Privacy

no code implementations15 May 2019 Mehmet Emre Gursoy, Acar Tamersoy, Stacey Truex, Wenqi Wei, Ling Liu

In this paper, we address the small user population problem by introducing the concept of Condensed Local Differential Privacy (CLDP) as a specialization of LDP, and develop a suite of CLDP protocols that offer desirable statistical utility while preserving privacy.

Cryptography and Security Databases

Differentially Private Model Publishing for Deep Learning

no code implementations3 Apr 2019 Lei Yu, Ling Liu, Calton Pu, Mehmet Emre Gursoy, Stacey Truex

However, when the training datasets are crowdsourced from individuals and contain sensitive information, the model parameters may encode private information and bear the risks of privacy leakage.

A Comparative Measurement Study of Deep Learning as a Service Framework

1 code implementation29 Oct 2018 Yanzhao Wu, Ling Liu, Calton Pu, Wenqi Cao, Semih Sahin, Wenqi Wei, Qi Zhang

Big data powered Deep Learning (DL) and its applications have blossomed in recent years, fueled by three technological trends: a large amount of digitized data openly accessible, a growing number of DL software frameworks in open source and commercial markets, and a selection of affordable parallel computing hardware devices.

A Computational Model for the Linguistic Notion of Morphological Paradigm

no code implementations COLING 2018 Miikka Silfverberg, Ling Liu, Mans Hulden

In supervised learning of morphological patterns, the strategy of generalizing inflectional tables into more abstract paradigms through alignment of the longest common subsequence found in an inflection table has been proposed as an efficient method to deduce the inflectional behavior of unseen word forms.

Adversarial Examples in Deep Learning: Characterization and Divergence

no code implementations29 Jun 2018 Wenqi Wei, Ling Liu, Margaret Loper, Stacey Truex, Lei Yu, Mehmet Emre Gursoy, Yanzhao Wu

The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data.

Adversarial Attack

Towards Demystifying Membership Inference Attacks

1 code implementation28 Jun 2018 Stacey Truex, Ling Liu, Mehmet Emre Gursoy, Lei Yu, Wenqi Wei

Our empirical results additionally show that (1) using the type of target model under attack within the attack model may not increase attack effectiveness and (2) collaborative learning in federated systems exposes vulnerabilities to membership inference risks when the adversary is a participant in the federation.

Cryptography and Security

Cannot find the paper you are looking for? You can Submit a new open access paper.