Search Results for author: Bin Cui

Found 36 papers, 22 papers with code

Don't Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript

no code implementations ICML 2020 Fangcheng Fu, Yuzheng Hu, Yihan He, Jiawei Jiang, Yingxia Shao, Ce Zhang, Bin Cui

Recent years have witnessed intensive research interests on training deep neural networks (DNNs) more efficiently by quantization-based compression methods, which facilitate DNNs training in two ways: (1) activations are quantized to shrink the memory consumption, and (2) gradients are quantized to decrease the communication cost.

Quantization

AutoML for Deep Recommender Systems: A Survey

no code implementations25 Mar 2022 Ruiqi Zheng, Liang Qu, Bin Cui, Yuhui Shi, Hongzhi Yin

To tackle this problem, Automated Machine Learning (AutoML) is introduced to automatically search for the proper candidates for different parts of deep recommender systems.

AutoML Recommendation Systems

ZOOMER: Boosting Retrieval on Web-scale Graphs by Regions of Interest

1 code implementation20 Mar 2022 Yuezihan Jiang, Yu Cheng, Hanyu Zhao, Wentao Zhang, Xupeng Miao, Yu He, Liang Wang, Zhi Yang, Bin Cui

We introduce ZOOMER, a system deployed at Taobao, the largest e-commerce platform in China, for training and serving GNN-based recommendations over web-scale graphs.

Information Gain Propagation: a new way to Graph Active Learning with Soft Labels

1 code implementation ICLR 2022 Wentao Zhang, Yexin Wang, Zhenbang You, Meng Cao, Ping Huang, Jiulong Shan, Zhi Yang, Bin Cui

Graph Neural Networks (GNNs) have achieved great success in various tasks, but their performance highly relies on a large number of labeled nodes, which typically requires considerable human effort.

Active Learning

PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm

1 code implementation1 Mar 2022 Wentao Zhang, Yu Shen, Zheyu Lin, Yang Li, Xiaosen Li, Wen Ouyang, Yangyu Tao, Zhi Yang, Bin Cui

Through deconstructing the message passing mechanism, PasCa presents a novel Scalable Graph Neural Architecture Paradigm (SGAP), together with a general architecture design space consisting of 150k different designs.

Neural Architecture Search

Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale

1 code implementation18 Jan 2022 Yang Li, Yu Shen, Huaijun Jiang, Wentao Zhang, Jixiang Li, Ji Liu, Ce Zhang, Bin Cui

The ever-growing demand and complexity of machine learning are putting pressure on hyper-parameter tuning systems: while the evaluation cost of models continues to increase, the scalability of state-of-the-arts starts to become a crucial bottleneck.

Dense-to-Sparse Gate for Mixture-of-Experts

1 code implementation29 Dec 2021 Xiaonan Nie, Shijie Cao, Xupeng Miao, Lingxiao Ma, Jilong Xue, Youshan Miao, Zichao Yang, Zhi Yang, Bin Cui

However, we found that the current approach of jointly training experts and the sparse gate introduces a negative impact on model accuracy, diminishing the efficiency of expensive large-scale model training.

K-Core Decomposition on Super Large Graphs with Limited Resources

no code implementations26 Dec 2021 Shicheng Gao, Jie Xu, Xiaosen Li, Fangcheng Fu, Wentao Zhang, Wen Ouyang, Yangyu Tao, Bin Cui

For example, the distributed K-core decomposition algorithm can scale to a large graph with 136 billion edges without losing correctness with our divide-and-conquer technique.

PointCLIP: Point Cloud Understanding by CLIP

2 code implementations4 Dec 2021 Renrui Zhang, Ziyu Guo, Wei zhang, Kunchang Li, Xupeng Miao, Bin Cui, Yu Qiao, Peng Gao, Hongsheng Li

On top of that, we design an inter-view adapter to better extract the global feature and adaptively fuse the few-shot knowledge learned from 3D into CLIP pre-trained in 2D.

Few-Shot Learning Transfer Learning

RIM: Reliable Influence-based Active Learning on Graphs

1 code implementation NeurIPS 2021 Wentao Zhang, Yexin Wang, Zhenbang You, Meng Cao, Ping Huang, Jiulong Shan, Zhi Yang, Bin Cui

Message passing is the core of most graph models such as Graph Convolutional Network (GCN) and Label Propagation (LP), which usually require a large number of clean labeled data to smooth out the neighborhood over the graph.

Active Learning

NAFS: A Simple yet Tough-to-Beat Baseline for Graph Representation Learning

no code implementations29 Sep 2021 Wentao Zhang, Zeang Sheng, Mingyu Yang, Yang Li, Yu Shen, Zhi Yang, Zichao Yang, Bin Cui

First, GNNs can learn higher-order structural information by stacking more layers but can not deal with large depth due to the over-smoothing issue.

Graph Representation Learning Link Prediction +1

Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation

1 code implementation13 Sep 2021 Yuxing Han, Ziniu Wu, Peizhi Wu, Rong Zhu, Jingyi Yang, Liang Wei Tan, Kai Zeng, Gao Cong, Yanzhao Qin, Andreas Pfadler, Zhengping Qian, Jingren Zhou, Jiangneng Li, Bin Cui

Therefore, we propose a new metric P-Error to evaluate the performance of CardEst methods, which overcomes the limitation of Q-Error and is able to reflect the overall end-to-end performance of CardEst methods.

Graph Attention Multi-Layer Perceptron

2 code implementations23 Aug 2021 Wentao Zhang, Ziqi Yin, Zeang Sheng, Wen Ouyang, Xiaosen Li, Yangyu Tao, Zhi Yang, Bin Cui

Graph neural networks (GNNs) have recently achieved state-of-the-art performance in many graph-based applications.

Graph Attention

Evaluating Deep Graph Neural Networks

no code implementations2 Aug 2021 Wentao Zhang, Zeang Sheng, Yuezihan Jiang, Yikuan Xia, Jun Gao, Zhi Yang, Bin Cui

Based on the experimental results, we answer the following two essential questions: (1) what actually leads to the compromised performance of deep GNNs; (2) when we need and how to build deep GNNs.

Graph Mining Node Classification

Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization

1 code implementation31 Jul 2021 Wentao Zhang, Zhi Yang, Yexin Wang, Yu Shen, Yang Li, Liang Wang, Bin Cui

Data selection methods, such as active learning and core-set selection, are useful tools for improving the data efficiency of deep learning models on large-scale datasets.

Active Learning Knowledge Graphs

ROD: Reception-aware Online Distillation for Sparse Graphs

1 code implementation25 Jul 2021 Wentao Zhang, Yuezihan Jiang, Yang Li, Zeang Sheng, Yu Shen, Xupeng Miao, Liang Wang, Zhi Yang, Bin Cui

Unfortunately, many real-world networks are sparse in terms of both edges and labels, leading to sub-optimal performance of GNNs.

Graph Learning Knowledge Distillation +4

VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition

3 code implementations19 Jul 2021 Yang Li, Yu Shen, Wentao Zhang, Jiawei Jiang, Bolin Ding, Yaliang Li, Jingren Zhou, Zhi Yang, Wentao Wu, Ce Zhang, Bin Cui

End-to-end AutoML has attracted intensive interests from both academia and industry, which automatically searches for ML pipelines in a space induced by feature engineering, algorithm/model selection, and hyper-parameter tuning.

AutoML Feature Engineering +1

OpenBox: A Generalized Black-box Optimization Service

7 code implementations1 Jun 2021 Yang Li, Yu Shen, Wentao Zhang, Yuanwei Chen, Huaijun Jiang, Mingchao Liu, Jiawei Jiang, Jinyang Gao, Wentao Wu, Zhi Yang, Ce Zhang, Bin Cui

Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, engineering, physics, and experimental design.

Experimental Design Transfer Learning

CausCF: Causal Collaborative Filtering for RecommendationEffect Estimation

no code implementations28 May 2021 Xu Xie, Zhaoyang Liu, Shiwen Wu, Fei Sun, Cihang Liu, Jiawei Chen, Jinyang Gao, Bin Cui, Bolin Ding

It is based on the idea that similar users not only have a similar taste on items, but also have similar treatment effect under recommendations.

Collaborative Filtering Recommendation Systems

GMLP: Building Scalable and Flexible Graph Neural Networks with Feature-Message Passing

no code implementations20 Apr 2021 Wentao Zhang, Yu Shen, Zheyu Lin, Yang Li, Xiaosen Li, Wen Ouyang, Yangyu Tao, Zhi Yang, Bin Cui

In recent studies, neural message passing has proved to be an effective way to design graph neural networks (GNNs), which have achieved state-of-the-art performance in many graph-based tasks.

Explore User Neighborhood for Real-time E-commerce Recommendation

no code implementations28 Feb 2021 Xu Xie, Fei Sun, Xiaoyong Yang, Zhao Yang, Jinyang Gao, Wenwu Ou, Bin Cui

On the one hand, it utilizes UI relations and user neighborhood to capture both global and local information.

Collaborative Filtering Recommendation Systems

Efficient Automatic CASH via Rising Bandits

no code implementations8 Dec 2020 Yang Li, Jiawei Jiang, Jinyang Gao, Yingxia Shao, Ce Zhang, Bin Cui

In this framework, the BO methods are used to solve the HPO problem for each ML algorithm separately, incorporating a much smaller hyperparameter space for BO methods.

Hyperparameter Optimization Multi-Armed Bandits

Efficient and Scalable Structure Learning for Bayesian Networks: Algorithms and Applications

no code implementations7 Dec 2020 Rong Zhu, Andreas Pfadler, Ziniu Wu, Yuxing Han, Xiaoke Yang, Feng Ye, Zhenping Qian, Jingren Zhou, Bin Cui

To resolve this, we propose a new structure learning algorithm LEAST, which comprehensively fulfills our business requirements as it attains high accuracy, efficiency and scalability at the same time.

Anomaly Detection

MFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements

6 code implementations5 Dec 2020 Yang Li, Yu Shen, Jiawei Jiang, Jinyang Gao, Ce Zhang, Bin Cui

Instead of sampling configurations randomly in HB, BOHB samples configurations based on a BO surrogate model, which is constructed with the high-fidelity measurements only.

Hyperparameter Optimization

FLAT: Fast, Lightweight and Accurate Method for Cardinality Estimation

1 code implementation18 Nov 2020 Rong Zhu, Ziniu Wu, Yuxing Han, Kai Zeng, Andreas Pfadler, Zhengping Qian, Jingren Zhou, Bin Cui

Despite decades of research, existing methods either over simplify the models only using independent factorization which leads to inaccurate estimates, or over complicate them by lossless conditional factorization without any independent assumption which results in slow probability computation.

Graph Neural Networks in Recommender Systems: A Survey

1 code implementation4 Nov 2020 Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, Bin Cui

With the explosive growth of online information, recommender systems play a key role to alleviate such information overload.

Graph Representation Learning Recommendation Systems

Contrastive Learning for Sequential Recommendation

1 code implementation27 Oct 2020 Xu Xie, Fei Sun, Zhaoyang Liu, Shiwen Wu, Jinyang Gao, Bolin Ding, Bin Cui

Sequential recommendation methods play a crucial role in modern recommender systems because of their ability to capture a user's dynamic interest from her/his historical interactions.

Contrastive Learning Data Augmentation +1

UniNet: Scalable Network Representation Learning with Metropolis-Hastings Sampling

1 code implementation10 Oct 2020 Xingyu Yao, Yingxia Shao, Bin Cui, Lei Chen

Finally, with the new edge sampler and random walk model abstraction, we carefully implement a scalable NRL framework called UniNet.

Representation Learning

DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition

no code implementations10 Oct 2019 Xupeng Miao, Nezihe Merve Gürel, Wentao Zhang, Zhichao Han, Bo Li, Wei Min, Xi Rao, Hansheng Ren, Yinan Shan, Yingxia Shao, Yujie Wang, Fan Wu, Hui Xue, Yaming Yang, Zitao Zhang, Yang Zhao, Shuai Zhang, Yujing Wang, Bin Cui, Ce Zhang

Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing problem.

X-Forest: Approximate Random Projection Trees for Similarity Measurement

1 code implementation25 Sep 2019 Yikai Zhao, Peiqing Chen, Zidong Zhao, Tong Yang, Jie Jiang, Bin Cui, Gong Zhang, Steve Uhlig

First, we introduced RP Trees into the tasks of similarity measurement such that accuracy is improved.

AHash: A Load-Balanced One Permutation Hash

1 code implementation25 Sep 2019 Chenxingyu Zhao, Jie Gui, Yixiao Guo, Jie Jiang, Tong Yang, Bin Cui, Gong Zhang

Unlike the densification to fill the empty bins after they undesirably occur, our design goal is to balance the load so as to reduce the empty bins in advance.

An Experimental Evaluation of Large Scale GBDT Systems

no code implementations3 Jul 2019 Fangcheng Fu, Jiawei Jiang, Yingxia Shao, Bin Cui

Gradient boosting decision tree (GBDT) is a widely-used machine learning algorithm in both data analytic competitions and real-world industrial applications.

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