Search Results for author: Wei. Lin

Found 28 papers, 8 papers with code

FusionStitching: Boosting Memory Intensive Computations for Deep Learning Workloads

no code implementations23 Sep 2020 Zhen Zheng, Pengzhan Zhao, Guoping Long, Feiwen Zhu, Kai Zhu, Wenyi Zhao, Lansong Diao, Jun Yang, Wei. Lin

We show in this work that memory intensive computations can result in severe performance problems due to off-chip memory access and CPU-GPU context switch overheads in a wide range of deep learning models.

Code Generation

One-shot Text Field Labeling using Attention and Belief Propagation for Structure Information Extraction

1 code implementation9 Sep 2020 Mengli Cheng, Minghui Qiu, Xing Shi, Jun Huang, Wei. Lin

Existing learning based methods for text labeling task usually require a large amount of labeled examples to train a specific model for each type of document.

One-Shot Learning Text Detection

Grasping Detection Network with Uncertainty Estimation for Confidence-Driven Semi-Supervised Domain Adaptation

no code implementations20 Aug 2020 Haiyue Zhu, Yiting Li, Fengjun Bai, Wenjie Chen, Xiaocong Li, Jun Ma, Chek Sing Teo, Pey Yuen Tao, Wei. Lin

The proposed grasping detection network specially provides a prediction uncertainty estimation mechanism by leveraging on Feature Pyramid Network (FPN), and the mean-teacher semi-supervised learning utilizes such uncertainty information to emphasizing the consistency loss only for those unlabelled data with high confidence, which we referred it as the confidence-driven mean teacher.

Domain Adaptation Semi-supervised Domain Adaptation

Pixel-wise Crowd Understanding via Synthetic Data

no code implementations30 Jul 2020 Qi. Wang, Junyu. Gao, Wei. Lin, Yuan Yuan

To be specific, 1) supervised crowd understanding: pre-train a crowd analysis model on the synthetic data, then fine-tune it using the real data and labels, which makes the model perform better on the real world; 2) crowd understanding via domain adaptation: translate the synthetic data to photo-realistic images, then train the model on translated data and labels.

Crowd Counting Domain Adaptation

FIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data

no code implementations29 Jul 2020 Yuexiang Xie, Zhen Wang, Yaliang Li, Bolin Ding, Nezihe Merve Gürel, Ce Zhang, Minlie Huang, Wei. Lin, Jingren Zhou

Then we instantiate this search strategy by optimizing both a dedicated graph neural network (GNN) and the adjacency tensor associated with the defined feature graph.

Recommendation Systems

Graph Structural-topic Neural Network

1 code implementation25 Jun 2020 Qingqing Long, Yilun Jin, Guojie Song, Yi Li, Wei. Lin

Specifically, we build topic models upon graphs using anonymous walks and Graph Anchor LDA, an LDA variant that selects significant structural patterns first, so as to alleviate the complexity and generate structural topics efficiently.

Topic Models

SwapText: Image Based Texts Transfer in Scenes

no code implementations CVPR 2020 Qiangpeng Yang, Hongsheng Jin, Jun Huang, Wei. Lin

First, a novel text swapping network is proposed to replace text labels only in the foreground image.

Image Generation Translation

Pixel-Level Self-Paced Learning for Super-Resolution

1 code implementation6 Mar 2020 Wei. Lin, Junyu. Gao, Qi. Wang, Xuelong. Li

Recently, lots of deep networks are proposed to improve the quality of predicted super-resolution (SR) images, due to its widespread use in several image-based fields.


AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search

1 code implementation13 Jan 2020 Daoyuan Chen, Yaliang Li, Minghui Qiu, Zhen Wang, Bofang Li, Bolin Ding, Hongbo Deng, Jun Huang, Wei. Lin, Jingren Zhou

Motivated by the necessity and benefits of task-oriented BERT compression, we propose a novel compression method, AdaBERT, that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks.

Knowledge Distillation Neural Architecture Search

NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization

4 code implementations10 Jan 2020 Qi. Wang, Junyu. Gao, Wei. Lin, Xuelong. Li

In the last decade, crowd counting and localization attract much attention of researchers due to its wide-spread applications, including crowd monitoring, public safety, space design, etc.

Crowd Counting

RPM-Oriented Query Rewriting Framework for E-commerce Keyword-Based Sponsored Search

no code implementations28 Oct 2019 Xiuying Chen, Daorui Xiao, Shen Gao, Guojun Liu, Wei. Lin, Bo Zheng, Dongyan Zhao, Rui Yan

Sponsored search optimizes revenue and relevance, which is estimated by Revenue Per Mille (RPM).

Characterizing Deep Learning Training Workloads on Alibaba-PAI

no code implementations14 Oct 2019 Mengdi Wang, Chen Meng, Guoping Long, Chuan Wu, Jun Yang, Wei. Lin, Yangqing Jia

One critical issue for efficiently operating practical AI clouds, is to characterize the computing and data transfer demands of these workloads, and more importantly, the training performance given the underlying software framework and hardware configurations.

DL2: A Deep Learning-driven Scheduler for Deep Learning Clusters

1 code implementation13 Sep 2019 Yanghua Peng, Yixin Bao, Yangrui Chen, Chuan Wu, Chen Meng, Wei. Lin

DL2 is a DL-driven scheduler for DL clusters, targeting global training job expedition by dynamically resizing resources allocated to jobs.

Fairness reinforcement-learning +2

C^3 Framework: An Open-source PyTorch Code for Crowd Counting

3 code implementations5 Jul 2019 Junyu. Gao, Wei. Lin, Bin Zhao, Dong Wang, Chenyu Gao, Jun Wen

This technical report attempts to provide efficient and solid kits addressed on the field of crowd counting, which is denoted as Crowd Counting Code Framework (C$^3$F).

Crowd Counting

Tag2Vec: Learning Tag Representations in Tag Networks

no code implementations19 Apr 2019 Junshan Wang, Zhicong Lu, Guojie Song, Yue Fan, Lun Du, Wei. Lin

Network embedding is a method to learn low-dimensional representation vectors for nodes in complex networks.

Network Embedding TAG

Learning from Synthetic Data for Crowd Counting in the Wild

no code implementations CVPR 2019 Qi. Wang, Junyu. Gao, Wei. Lin, Yuan Yuan

Secondly, we propose two schemes that exploit the synthetic data to boost the performance of crowd counting in the wild: 1) pretrain a crowd counter on the synthetic data, then finetune it using the real data, which significantly prompts the model's performance on real data; 2) propose a crowd counting method via domain adaptation, which can free humans from heavy data annotations.

Crowd Counting Domain Adaptation

AliGraph: A Comprehensive Graph Neural Network Platform

no code implementations23 Feb 2019 Rong Zhu, Kun Zhao, Hongxia Yang, Wei. Lin, Chang Zhou, Baole Ai, Yong Li, Jingren Zhou

An increasing number of machine learning tasks require dealing with large graph datasets, which capture rich and complex relationship among potentially billions of elements.

Distributed, Parallel, and Cluster Computing

EENMF: An End-to-End Neural Matching Framework for E-Commerce Sponsored Search

no code implementations4 Dec 2018 Wenjin Wu, Guojun Liu, Hui Ye, Chenshuang Zhang, Tianshu Wu, Daorui Xiao, Wei. Lin, Xiaoyu Zhu

In the real traffic of a large-scale e-commerce sponsored search, the proposed approach significantly outperforms the baseline.


Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks

no code implementations21 Nov 2018 Mengdi Wang, Qing Zhang, Jun Yang, Xiaoyuan Cui, Wei. Lin

In this method, the network is viewed as a computational graph, in which the vertices denote the computation nodes and edges represent the information flow.

Knowledge Distillation Model Compression

FusionStitching: Deep Fusion and Code Generation for Tensorflow Computations on GPUs

no code implementations13 Nov 2018 Guoping Long, Jun Yang, Kai Zhu, Wei. Lin

In recent years, there is a surge on machine learning applications in industry.

Distributed, Parallel, and Cluster Computing Mathematical Software

Beyond Keywords and Relevance: A Personalized Ad Retrieval Framework in E-Commerce Sponsored Search

no code implementations29 Dec 2017 Su Yan, Wei. Lin, Tianshu Wu, Daorui Xiao, Xu Zheng, Bo Wu, Kaipeng Liu

Given a search request, ad retrieval module rewrites the query into bidding keywords, and uses these keywords as keys to select Top N ads through inverted indexes.


Nonsparse learning with latent variables

no code implementations7 Oct 2017 Zemin Zheng, Jinchi Lv, Wei. Lin

A new methodology of nonsparse learning with latent variables (NSL) is proposed to simultaneously recover the significant observable predictors and latent factors as well as their effects.

Model Selection Sparse Learning

SOFAR: large-scale association network learning

no code implementations26 Apr 2017 Yoshimasa Uematsu, Yingying Fan, Kun Chen, Jinchi Lv, Wei. Lin

Many modern big data applications feature large scale in both numbers of responses and predictors.

Neural Networks Models for Entity Discovery and Linking

no code implementations11 Nov 2016 Dan Liu, Wei. Lin, Shiliang Zhang, Si Wei, Hui Jiang

This paper describes the USTC_NELSLIP systems submitted to the Trilingual Entity Detection and Linking (EDL) track in 2016 TAC Knowledge Base Population (KBP) contests.

Clustering Entity Linking +1

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