Zobrazeno 1 - 10
of 2 616
pro vyhledávání: '"Abdelzaher A"'
Autor:
Sun, Dachun, Wang, Ruijie, Li, Jinning, Han, Ruipeng, Liu, Xinyi, Lyu, You, Abdelzaher, Tarek
This paper addresses the problem of optimizing the allocation of labeling resources for semi-supervised belief representation learning in social networks. The objective is to strategically identify valuable messages on social media graphs that are wo
Externí odkaz:
http://arxiv.org/abs/2410.19176
Autor:
Cui, Hang, Abdelzaher, Tarek
Echo chambers and online discourses have become prevalent social phenomena where communities engage in dramatic intra-group confirmations and inter-group hostility. Polarization detection is a rising research topic for detecting and identifying such
Externí odkaz:
http://arxiv.org/abs/2409.07716
Autor:
Cui, Hang, Abdelzaher, Tarek
This paper introduces a fine-grained contrastive learning scheme for unsupervised node clustering. Previous clustering methods only focus on a small feature set (class-dependent features), which demonstrates explicit clustering characteristics, ignor
Externí odkaz:
http://arxiv.org/abs/2409.07718
Autor:
Cui, Hang, Abdelzaher, Tarek
In the broader machine learning literature, data-generation methods demonstrate promising results by generating additional informative training examples via augmenting sparse labels. Such methods are less studied in graphs due to the intricate depend
Externí odkaz:
http://arxiv.org/abs/2409.07712
The growing richness of large-scale datasets has been crucial in driving the rapid advancement and wide adoption of machine learning technologies. The massive collection and usage of data, however, pose an increasing risk for people's private and sen
Externí odkaz:
http://arxiv.org/abs/2405.14981
Autor:
Kimura, Tomoyoshi, Li, Jinyang, Wang, Tianshi, Kara, Denizhan, Chen, Yizhuo, Hu, Yigong, Wang, Ruijie, Wigness, Maggie, Liu, Shengzhong, Srivastava, Mani, Diggavi, Suhas, Abdelzaher, Tarek
This paper demonstrates the potential of vibration-based Foundation Models (FMs), pre-trained with unlabeled sensing data, to improve the robustness of run-time inference in (a class of) IoT applications. A case study is presented featuring a vehicle
Externí odkaz:
http://arxiv.org/abs/2404.02461
Autor:
Wang, Tianshi, Li, Jinyang, Wang, Ruijie, Kara, Denizhan, Liu, Shengzhong, Wertheimer, Davis, Viros-i-Martin, Antoni, Ganti, Raghu, Srivatsa, Mudhakar, Abdelzaher, Tarek
This paper introduces SudokuSens, a generative framework for automated generation of training data in machine-learning-based Internet-of-Things (IoT) applications, such that the generated synthetic data mimic experimental configurations not encounter
Externí odkaz:
http://arxiv.org/abs/2402.02275
Autor:
Liu, Shengzhong, Kimura, Tomoyoshi, Liu, Dongxin, Wang, Ruijie, Li, Jinyang, Diggavi, Suhas, Srivastava, Mani, Abdelzaher, Tarek
This paper proposes a novel contrastive learning framework, called FOCAL, for extracting comprehensive features from multimodal time-series sensing signals through self-supervised training. Existing multimodal contrastive frameworks mostly rely on th
Externí odkaz:
http://arxiv.org/abs/2310.20071
Autor:
Sun, Chenkai, Li, Jinning, Fung, Yi R., Chan, Hou Pong, Abdelzaher, Tarek, Zhai, ChengXiang, Ji, Heng
Automatic response forecasting for news media plays a crucial role in enabling content producers to efficiently predict the impact of news releases and prevent unexpected negative outcomes such as social conflict and moral injury. To effectively fore
Externí odkaz:
http://arxiv.org/abs/2310.13297
Autor:
Liu, Xinyi, Wang, Ruijie, Sun, Dachun, Li, Jinning, Youn, Christina, Lyu, You, Zhan, Jianyuan, Wu, Dayou, Xu, Xinhe, Liu, Mingjun, Lei, Xinshuo, Xu, Zhihao, Zhang, Yutong, Li, Zehao, Yang, Qikai, Abdelzaher, Tarek
This paper addresses influence pathway discovery, a key emerging problem in today's online media. We propose a discovery algorithm that leverages recently published work on unsupervised interpretable ideological embedding, a mapping of ideological be
Externí odkaz:
http://arxiv.org/abs/2309.16071