no code implementations • EMNLP 2021 • Chenhan Yuan, Hoda Eldardiry
We propose a VAE-based unsupervised relation extraction technique that overcomes this limitation by using the classifications as an intermediate variable instead of a latent variable.
no code implementations • 1 Mar 2024 • Jiaying Gong, Hoda Eldardiry
The MFS-HVE semantic feature extractors are developed to extract both textual and visual features.
1 code implementation • 13 Feb 2024 • Jiaying Gong, Hoda Eldardiry
We propose HyperPAVE, a multi-label zero-shot attribute value extraction model that leverages inductive inference in heterogeneous hypergraphs.
no code implementations • 7 Oct 2023 • Chenhan Yuan, Hoda Eldardiry
This helps address the lack of interpretability in existing TKGR models and provides a universal explanation approach applicable across various models.
no code implementations • 25 Aug 2023 • Humaid Ahmed Desai, Amr Hilal, Hoda Eldardiry
FL emerges as a privacy-enforcing sub-domain of machine learning that enables model training on client devices, eliminating the necessity to share private data with a central server.
no code implementations • 16 Aug 2023 • Jiaying Gong, Wei-Te Chen, Hoda Eldardiry
Existing attribute-value extraction (AVE) models require large quantities of labeled data for training.
no code implementations • 2 Jun 2022 • Afrina Tabassum, Muntasir Wahed, Hoda Eldardiry, Ismini Lourentzou
One of the challenges in contrastive learning is the selection of appropriate \textit{hard negative} examples, in the absence of label information.
no code implementations • 8 Dec 2021 • Jiaying Gong, Hoda Eldardiry
We learn the representations of both seen and unseen relations with augmented instances and prompts.
no code implementations • 19 Apr 2021 • Vasanth Reddy, Hoda Eldardiry, Almuatazbellah Boker
This work presents a technique for learning systems, where the learning process is guided by knowledge of the physics of the system.
1 code implementation • 13 Nov 2020 • Jiaying Gong, Hoda Eldardiry
We propose a zero-shot learning relation classification (ZSLRC) framework that improves on state-of-the-art by its ability to recognize novel relations that were not present in training data.
no code implementations • 14 Oct 2020 • Hongjie Chen, Ryan A. Rossi, Kanak Mahadik, Sungchul Kim, Hoda Eldardiry
GraphDF is a hybrid forecasting framework that consists of a relational global and relational local model.
no code implementations • 26 Sep 2020 • Chenhan Yuan, Ryan Rossi, Andrew Katz, Hoda Eldardiry
In this paper, we relax this strong assumption by a weaker distant supervision assumption to address the second issue and propose a novel sentence distribution estimator model to address the first problem.
no code implementations • 26 Sep 2020 • Chenhan Yuan, Ryan Rossi, Andrew Katz, Hoda Eldardiry
To address this issue, we propose a Clustering-based Unsupervised generative Relation Extraction (CURE) framework that leverages an "Encoder-Decoder" architecture to perform self-supervised learning so the encoder can extract relation information.
no code implementations • 25 Sep 2020 • Eslam Hussein, Hoda Eldardiry
Our audit study investigates (a) factors that might influence the search algorithms of Amazon and (b) personalization attributes that contribute to amplifying the amount of misinformation recommended to users in their search results and recommendations.
no code implementations • 25 Sep 2020 • Hongjie Chen, Ryan A. Rossi, Kanak Mahadik, Hoda Eldardiry
We propose a novel context integrated relational model, Context Integrated Graph Neural Network (CIGNN), which leverages the temporal, relational, spatial, and dynamic contextual dependencies for multi-step ahead demand forecasting.
no code implementations • 10 Aug 2020 • Seifeldeen Eteifa, Hesham A. Rakha, Hoda Eldardiry
Vehicle acceleration and deceleration maneuvers at traffic signals results in significant fuel and energy consumption levels.
no code implementations • 10 Aug 2020 • Milad Afzalan, Farrokh Jazizadeh, Hoda Eldardiry
In the first stage, load shapes are clustered by allowing a large number of clusters to accurately capture variations in energy use patterns and cluster centroids are extracted by accounting for shape misalignments.
2 code implementations • IJCAI 2018 • Nesreen K. Ahmed, Ryan Rossi, John Boaz Lee, Theodore L. Willke, Rong Zhou, Xiangnan Kong, Hoda Eldardiry
Random walks are at the heart of many existing network embedding methods.
no code implementations • 27 Oct 2017 • Ryan A. Rossi, Nesreen K. Ahmed, Hoda Eldardiry, Rong Zhou
Multi-label classification is an important learning problem with many applications.
no code implementations • 25 Oct 2017 • Nesreen K. Ahmed, Ryan A. Rossi, Rong Zhou, John Boaz Lee, Xiangnan Kong, Theodore L. Willke, Hoda Eldardiry
To make these methods more generally applicable, we propose a framework for inductive network representation learning based on the notion of attributed random walk that is not tied to node identity and is instead based on learning a function $\Phi : \mathrm{\rm \bf x} \rightarrow w$ that maps a node attribute vector $\mathrm{\rm \bf x}$ to a type $w$.
no code implementations • 14 Sep 2017 • Nesreen K. Ahmed, Ryan A. Rossi, Rong Zhou, John Boaz Lee, Xiangnan Kong, Theodore L. Willke, Hoda Eldardiry
Random walks are at the heart of many existing deep learning algorithms for graph data.