Search Results for author: Jiajun Shen

Found 27 papers, 12 papers with code

Model-free Resilient Controller Design based on Incentive Feedback Stackelberg Game and Q-learning

no code implementations13 Mar 2024 Jiajun Shen, Fengjun Li, Morteza Hashemi, Huazhen Fang

In the swift evolution of Cyber-Physical Systems (CPSs) within intelligent environments, especially in the industrial domain shaped by Industry 4. 0, the surge in development brings forth unprecedented security challenges.

Q-Learning

Exploring Federated Self-Supervised Learning for General Purpose Audio Understanding

no code implementations5 Feb 2024 Yasar Abbas Ur Rehman, Kin Wai Lau, Yuyang Xie, Lan Ma, Jiajun Shen

The integration of Federated Learning (FL) and Self-supervised Learning (SSL) offers a unique and synergetic combination to exploit the audio data for general-purpose audio understanding, without compromising user data privacy.

Federated Learning Retrieval +1

Asynchronous Local-SGD Training for Language Modeling

1 code implementation17 Jan 2024 Bo Liu, Rachita Chhaparia, Arthur Douillard, Satyen Kale, Andrei A. Rusu, Jiajun Shen, Arthur Szlam, Marc'Aurelio Ranzato

Local stochastic gradient descent (Local-SGD), also referred to as federated averaging, is an approach to distributed optimization where each device performs more than one SGD update per communication.

Distributed Optimization Language Modelling

DiLoCo: Distributed Low-Communication Training of Language Models

no code implementations14 Nov 2023 Arthur Douillard, Qixuan Feng, Andrei A. Rusu, Rachita Chhaparia, Yani Donchev, Adhiguna Kuncoro, Marc'Aurelio Ranzato, Arthur Szlam, Jiajun Shen

In this work, we propose a distributed optimization algorithm, Distributed Low-Communication (DiLoCo), that enables training of language models on islands of devices that are poorly connected.

Distributed Optimization

Source-Aware Embedding Training on Heterogeneous Information Networks

no code implementations10 Jul 2023 Tsai Hor Chan, Chi Ho Wong, Jiajun Shen, Guosheng Yin

Heterogeneous information networks (HINs) have been extensively applied to real-world tasks, such as recommendation systems, social networks, and citation networks.

Graph Embedding Network Embedding +1

SL3D: Self-supervised-Self-labeled 3D Recognition

1 code implementation30 Oct 2022 Fernando Julio Cendra, Lan Ma, Jiajun Shen, Xiaojuan Qi

SL3D is a generic framework and can be applied to solve different 3D recognition tasks, including classification, object detection, and semantic segmentation.

Clustering Object +5

Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing

1 code implementation20 Jul 2022 Xin Yu, Peng Dai, Wenbo Li, Lan Ma, Jiajun Shen, Jia Li, Xiaojuan Qi

With the rapid development of mobile devices, modern widely-used mobile phones typically allow users to capture 4K resolution (i. e., ultra-high-definition) images.

Image Enhancement Image Restoration +1

Federated Self-supervised Learning for Video Understanding

2 code implementations5 Jul 2022 Yasar Abbas Ur Rehman, Yan Gao, Jiajun Shen, Pedro Porto Buarque de Gusmao, Nicholas Lane

The ubiquity of camera-enabled mobile devices has lead to large amounts of unlabelled video data being produced at the edge.

 Ranked #1 on Action Recognition on UCF-101 (Accuracy metric)

Action Recognition Federated Learning +3

Reconstruct Face from Features Using GAN Generator as a Distribution Constraint

no code implementations9 Jun 2022 Xingbo Dong, Zhihui Miao, Lan Ma, Jiajun Shen, Zhe Jin, Zhenhua Guo, Andrew Beng Jin Teoh

Yet, the security and privacy of the extracted features from deep learning models (deep features) have been often overlooked.

Face Recognition Privacy Preserving

Video Demoireing with Relation-Based Temporal Consistency

1 code implementation CVPR 2022 Peng Dai, Xin Yu, Lan Ma, Baoheng Zhang, Jia Li, Wenbo Li, Jiajun Shen, Xiaojuan Qi

Moire patterns, appearing as color distortions, severely degrade image and video qualities when filming a screen with digital cameras.

Relation

Abandoning the Bayer-Filter to See in the Dark

1 code implementation CVPR 2022 Xingbo Dong, Wanyan Xu, Zhihui Miao, Lan Ma, Chao Zhang, Jiewen Yang, Zhe Jin, Andrew Beng Jin Teoh, Jiajun Shen

Next, a fully convolutional network is proposed to achieve the low-light image enhancement by fusing colored raw data with synthesized monochrome raw data.

Low-Light Image Enhancement

Recurring the Transformer for Video Action Recognition

no code implementations CVPR 2022 Jiewen Yang, Xingbo Dong, Liujun Liu, Chao Zhang, Jiajun Shen, Dahai Yu

Besides, the proposed RViT can work on both fixed-length and variant-length video clips properly without requiring large GPU memory thanks to the frame by frame processing flow.

Action Recognition Representation Learning +3

Interpretable performance analysis towards offline reinforcement learning: A dataset perspective

no code implementations12 May 2021 Chenyang Xi, Bo Tang, Jiajun Shen, Xinfu Liu, Feiyu Xiong, Xueying Li

We make it open-source for fair and comprehensive competitions between offline RL algorithms with complete datasets and checkpoints being provided.

Offline RL Q-Learning +2

Scalable Graph Neural Networks for Heterogeneous Graphs

1 code implementation19 Nov 2020 Lingfan Yu, Jiajun Shen, Jinyang Li, Adam Lerer

Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data.

Node Property Prediction

Revisiting Self-Training for Neural Sequence Generation

1 code implementation ICLR 2020 Junxian He, Jiatao Gu, Jiajun Shen, Marc'Aurelio Ranzato

In this work, we first empirically show that self-training is able to decently improve the supervised baseline on neural sequence generation tasks.

Machine Translation Text Summarization +1

The Source-Target Domain Mismatch Problem in Machine Translation

no code implementations EACL 2021 Jiajun Shen, Peng-Jen Chen, Matt Le, Junxian He, Jiatao Gu, Myle Ott, Michael Auli, Marc'Aurelio Ranzato

While we live in an increasingly interconnected world, different places still exhibit strikingly different cultures and many events we experience in our every day life pertain only to the specific place we live in.

Machine Translation Translation

PyTorch-BigGraph: A Large-scale Graph Embedding System

1 code implementation28 Mar 2019 Adam Lerer, Ledell Wu, Jiajun Shen, Timothee Lacroix, Luca Wehrstedt, Abhijit Bose, Alex Peysakhovich

Graph embedding methods produce unsupervised node features from graphs that can then be used for a variety of machine learning tasks.

 Ranked #1 on Link Prediction on YouTube (Macro F1 metric)

Graph Embedding graph partitioning +1

Deformable Classifiers

no code implementations18 Dec 2017 Jiajun Shen, Yali Amit

In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and a transformation of the object image to a reference instantiation is computed in terms of the classifier output, separately for each class.

Object Object Recognition +1

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