Search Results for author: Latifur Khan

Found 16 papers, 6 papers with code

ConfliBERT: A Pre-trained Language Model for Political Conflict and Violence

1 code implementation NAACL 2022 Yibo Hu, MohammadSaleh Hosseini, Erick Skorupa Parolin, Javier Osorio, Latifur Khan, Patrick Brandt, Vito D’Orazio

To help advance research in political science, we introduce ConfliBERT, a domain-specific pre-trained language model for conflict and political violence.

Language Modelling

Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness

no code implementations19 Feb 2024 Chen Zhao, Feng Mi, Xintao Wu, Kai Jiang, Latifur Khan, Feng Chen

Theoretical analysis yields sub-linear upper bounds for both loss regret and the cumulative violation of fairness constraints.

Fairness Meta-Learning

Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously

1 code implementation23 Nov 2023 Chen Zhao, Kai Jiang, Xintao Wu, Haoliang Wang, Latifur Khan, Christan Grant, Feng Chen

The endeavor to preserve the generalization of a fair and invariant classifier across domains, especially in the presence of distribution shifts, becomes a significant and intricate challenge in machine learning.

Domain Generalization Fairness +1

Towards Fair Disentangled Online Learning for Changing Environments

no code implementations31 May 2023 Chen Zhao, Feng Mi, Xintao Wu, Kai Jiang, Latifur Khan, Christan Grant, Feng Chen

To this end, in this paper, we propose a novel algorithm under the assumption that data collected at each time can be disentangled with two representations, an environment-invariant semantic factor and an environment-specific variation factor.

Fairness

An Automated Vulnerability Detection Framework for Smart Contracts

no code implementations20 Jan 2023 Feng Mi, Chen Zhao, Zhuoyi Wang, Sadaf MD Halim, Xiaodi Li, Zhouxiang Wu, Latifur Khan, Bhavani Thuraisingham

With the increase of the adoption of blockchain technology in providing decentralized solutions to various problems, smart contracts have become more popular to the point that billions of US Dollars are currently exchanged every day through such technology.

Metric Learning Vulnerability Detection

Controllable Fake Document Infilling for Cyber Deception

1 code implementation18 Oct 2022 Yibo Hu, Yu Lin, Erick Skorupa Parolin, Latifur Khan, Kevin Hamlen

Recent works in cyber deception study how to deter malicious intrusion by generating multiple fake versions of a critical document to impose costs on adversaries who need to identify the correct information.

Adaptive Fairness-Aware Online Meta-Learning for Changing Environments

no code implementations20 May 2022 Chen Zhao, Feng Mi, Xintao Wu, Kai Jiang, Latifur Khan, Feng Chen

Furthermore, to determine a good model parameter at each round, we propose a novel adaptive fairness-aware online meta-learning algorithm, namely FairSAOML, which is able to adapt to changing environments in both bias control and model precision.

Fairness Meta-Learning

Uncertainty-Aware Reliable Text Classification

1 code implementation15 Jul 2021 Yibo Hu, Latifur Khan

Extensive empirical experiments demonstrate that our model based on evidential uncertainty outperforms other counterparts for detecting OOD examples.

Outlier Detection Out of Distribution (OOD) Detection +2

Towards Self-Adaptive Metric Learning On the Fly

no code implementations3 Apr 2021 Yang Gao, Yi-Fan Li, Swarup Chandra, Latifur Khan, Bhavani Thuraisingham

In this paper, we present a new online metric learning framework that attempts to tackle the challenge by learning an ANN-based metric with adaptive model complexity from a stream of constraints.

Image Classification Image Retrieval +2

SetConv: A New Approach for Learning from Imbalanced Data

no code implementations EMNLP 2020 Yang Gao, Yi-Fan Li, Yu Lin, Charu Aggarwal, Latifur Khan

For many real-world classification problems, e. g., sentiment classification, most existing machine learning methods are biased towards the majority class when the Imbalance Ratio (IR) is high.

BIG-bench Machine Learning Classification +3

A Primal-Dual Subgradient Approachfor Fair Meta Learning

1 code implementation26 Sep 2020 Chen Zhao, Feng Chen, Zhuoyi Wang, Latifur Khan

In this work, we propose a Primal-Dual Fair Meta-learning framework, namely PDFM, which learns to train fair machine learning models using only a few examples based on data from related tasks.

Fairness Few-Shot Learning

Deep Learning on Knowledge Graph for Recommender System: A Survey

no code implementations25 Mar 2020 Yang Gao, Yi-Fan Li, Yu Lin, Hang Gao, Latifur Khan

Recent advances in research have demonstrated the effectiveness of knowledge graphs (KG) in providing valuable external knowledge to improve recommendation systems (RS).

Graph Embedding Knowledge Graphs +1

Co-Representation Learning For Classification and Novel Class Detection via Deep Networks

no code implementations13 Nov 2018 Zhuoyi Wang, Zelun Kong, Hemeng Tao, Swarup Chandra, Latifur Khan

In this paper, we address this key challenge by proposing a semi-supervised multi-task learning framework called \sysname{} which aims to intrinsically search for a latent space suitable for detecting labels of instances from both known and unknown classes.

General Classification Multi-Task Learning +1

Cause Identification from Aviation Safety Incident Reports via Weakly Supervised Semantic Lexicon Construction

no code implementations16 Jan 2014 Muhammad Arshad Ul Abedin, Vincent Ng, Latifur Khan

The Aviation Safety Reporting System collects voluntarily submitted reports on aviation safety incidents to facilitate research work aiming to reduce such incidents.

General Classification text-classification +1

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