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.
1 code implementation • 27 Nov 2023 • Xupeng Miao, Chunan Shi, Jiangfei Duan, Xiaoli Xi, Dahua Lin, Bin Cui, Zhihao Jia
This paper aims to reduce the monetary cost for serving LLMs by leveraging preemptible GPU instances on modern clouds, which offer accesses to spare GPUs at a much cheaper price than regular instances but may be preempted by the cloud at any time.
1 code implementation • 27 Nov 2023 • Hailin Zhang, Penghao Zhao, Xupeng Miao, Yingxia Shao, Zirui Liu, Tong Yang, Bin Cui
Learnable embedding vector is one of the most important applications in machine learning, and is widely used in various database-related domains.
no code implementations • 17 Oct 2023 • Xinyi Gao, Wentao Zhang, Junliang Yu, Yingxia Shao, Quoc Viet Hung Nguyen, Bin Cui, Hongzhi Yin
To further accelerate Scalable GNNs inference in this inductive setting, we propose an online propagation framework and two novel node-adaptive propagation methods that can customize the optimal propagation depth for each node based on its topological information and thereby avoid redundant feature propagation.
1 code implementation • 23 Sep 2023 • Hailin Zhang, Yujing Wang, Qi Chen, Ruiheng Chang, Ting Zhang, Ziming Miao, Yingyan Hou, Yang Ding, Xupeng Miao, Haonan Wang, Bochen Pang, Yuefeng Zhan, Hao Sun, Weiwei Deng, Qi Zhang, Fan Yang, Xing Xie, Mao Yang, Bin Cui
We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.
no code implementations • 5 Sep 2023 • Yang Li, Huaijun Jiang, Yu Shen, Yide Fang, Xiaofeng Yang, Danqing Huang, Xinyi Zhang, Wentao Zhang, Ce Zhang, Peng Chen, Bin Cui
The distributed data analytic system -- Spark is a common choice for processing massive volumes of heterogeneous data, while it is challenging to tune its parameters to achieve high performance.
no code implementations • 17 Aug 2023 • Tianmeng Yang, Min Zhou, Yujing Wang, Zhengjie Lin, Lujia Pan, Bin Cui, Yunhai Tong
Graph Active Learning (GAL), which aims to find the most informative nodes in graphs for annotation to maximize the Graph Neural Networks (GNNs) performance, has attracted many research efforts but remains non-trivial challenges.
1 code implementation • 4 Aug 2023 • Ling Yang, Ye Tian, Minkai Xu, Zhongyi Liu, Shenda Hong, Wei Qu, Wentao Zhang, Bin Cui, Muhan Zhang, Jure Leskovec
To address this issue, we propose to learn a new powerful graph representation space by directly labeling nodes' diverse local structures for GNN-to-MLP distillation.
no code implementations • 28 Jul 2023 • Jie Liu, Mengting He, Xuequn Shang, Jieming Shi, Bin Cui, Hongzhi Yin
By swapping the context embeddings between nodes and edges and measuring the agreement in the embedding space, we enable the mutual detection of node and edge anomalies.
no code implementations • 5 Jul 2023 • Yujie Wang, Youhe Jiang, Xupeng Miao, Fangcheng Fu, Xiaonan Nie, Bin Cui
Transformer models have emerged as the leading approach for achieving state-of-the-art performance across various application domains, serving as the foundation for advanced large-scale deep learning (DL) models.
1 code implementation • 28 Jun 2023 • Ling Yang, Jiayi Zheng, Heyuan Wang, Zhongyi Liu, Zhilin Huang, Shenda Hong, Wentao Zhang, Bin Cui
To remove class spurious feature caused by distribution shifts, we propose Individual Graph Information Bottleneck (I-GIB) which discards irrelevant information by minimizing the mutual information between the input graph and its embeddings.
no code implementations • 27 May 2023 • Zihao Yu, Haoyang Li, Fangcheng Fu, Xupeng Miao, Bin Cui
The key intuition behind our approach is to utilize the semantic mapping between the minor modifications on the input text and the affected regions on the output image.
1 code implementation • 26 Apr 2023 • Huaijun Jiang, Yu Shen, Yang Li, Wentao Zhang, Ce Zhang, Bin Cui
Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, experimental design, and database knob tuning.
no code implementations • 8 Apr 2023 • Xiaonan Nie, Xupeng Miao, Zilong Wang, Zichao Yang, Jilong Xue, Lingxiao Ma, Gang Cao, Bin Cui
We first present an empirical analysis on the problems and opportunities of training MoE models, which motivates us to overcome the routing imbalance and fluctuation problems by a dynamic expert management and device placement mechanism.
no code implementations • 10 Mar 2023 • Xinyi Zhang, Zhuo Chang, Hong Wu, Yang Li, Jia Chen, Jian Tan, Feifei Li, Bin Cui
To tune different components for DBMS, a coordinating mechanism is needed to make the multiple agents cognizant of each other.
no code implementations • 6 Mar 2023 • Xiaonan Nie, Yi Liu, Fangcheng Fu, Jinbao Xue, Dian Jiao, Xupeng Miao, Yangyu Tao, Bin Cui
Recent years have witnessed the unprecedented achievements of large-scale pre-trained models, especially the Transformer models.
no code implementations • 12 Feb 2023 • Tianyi Bai, Yang Li, Yu Shen, Xinyi Zhang, Wentao Zhang, Bin Cui
A wide spectrum of design and decision problems, including parameter tuning, A/B testing and drug design, intrinsically are instances of black-box optimization.
no code implementations • 8 Feb 2023 • Yu Shen, Xinyuyang Ren, Yupeng Lu, Huaijun Jiang, Huanyong Xu, Di Peng, Yang Li, Wentao Zhang, Bin Cui
When applying transfer learning to accelerate the tuning process, we notice two domain-specific challenges: 1) most previous work focus on transferring tuning history, while expert knowledge from Spark engineers is of great potential to improve the tuning performance but is not well studied so far; 2) history tasks should be carefully utilized, where using dissimilar ones lead to a deteriorated performance in production.
no code implementations • 7 Feb 2023 • Yu Shen, Yupeng Lu, Yang Li, Yaofeng Tu, Wentao Zhang, Bin Cui
To tackle this issue and further enhance the ensemble performance, we propose DivBO, a diversity-aware framework to inject explicit search of diversity into the CASH problems.
2 code implementations • 25 Nov 2022 • Xupeng Miao, Yujie Wang, Youhe Jiang, Chunan Shi, Xiaonan Nie, Hailin Zhang, Bin Cui
Transformer models have achieved state-of-the-art performance on various domains of applications and gradually becomes the foundations of the advanced large deep learning (DL) models.
1 code implementation • 21 Nov 2022 • Ling Yang, Zhilin Huang, Yang song, Shenda Hong, Guohao Li, Wentao Zhang, Bin Cui, Bernard Ghanem, Ming-Hsuan Yang
Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images.
no code implementations • 1 Nov 2022 • Xinyi Gao, Wentao Zhang, Yingxia Shao, Quoc Viet Hung Nguyen, Bin Cui, Hongzhi Yin
Graph neural networks (GNNs) have demonstrated excellent performance in a wide range of applications.
no code implementations • 1 Nov 2022 • Yingxia Shao, Hongzheng Li, Xizhi Gu, Hongbo Yin, Yawen Li, Xupeng Miao, Wentao Zhang, Bin Cui, Lei Chen
In recent years, many efforts have been made on distributed GNN training, and an array of training algorithms and systems have been proposed.
1 code implementation • 28 Sep 2022 • Ziyu Guo, Renrui Zhang, Longtian Qiu, Xianzheng Ma, Xupeng Miao, Xuming He, Bin Cui
Contrastive Language-Image Pre-training (CLIP) has been shown to learn visual representations with great transferability, which achieves promising accuracy for zero-shot classification.
Ranked #4 on
Training-free 3D Point Cloud Classification
on ScanObjectNN
(using extra training data)
Training-free 3D Point Cloud Classification
Transfer Learning
+1
2 code implementations • 2 Sep 2022 • Ling Yang, Zhilong Zhang, Yang song, Shenda Hong, Runsheng Xu, Yue Zhao, Yingxia Shao, Wentao Zhang, Bin Cui, Ming-Hsuan Yang
This survey aims to provide a contextualized, in-depth look at the state of diffusion models, identifying the key areas of focus and pointing to potential areas for further exploration.
no code implementations • 29 Jul 2022 • Fangcheng Fu, Xupeng Miao, Jiawei Jiang, Huanran Xue, Bin Cui
Vertical federated learning (VFL) is an emerging paradigm that allows different parties (e. g., organizations or enterprises) to collaboratively build machine learning models with privacy protection.
1 code implementation • 19 Jun 2022 • Yang Li, Yu Shen, Wentao Zhang, 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.
1 code implementation • 17 Jun 2022 • Wentao Zhang, Zheyu Lin, Yu Shen, Yang Li, Zhi Yang, Bin Cui
Graph neural networks (GNNs) have been intensively applied to various graph-based applications.
2 code implementations • 17 Jun 2022 • Wentao Zhang, Zeang Sheng, Mingyu Yang, Yang Li, Yu Shen, Zhi 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.
no code implementations • 16 Jun 2022 • Fangcheng Fu, Huanran Xue, Yong Cheng, Yangyu Tao, Bin Cui
First, to address the functionality of VFL models, we propose the federated source layers to unite the data from different parties.
1 code implementation • 9 Jun 2022 • Wentao Zhang, Ziqi Yin, Zeang Sheng, Yang Li, Wen Ouyang, Xiaosen Li, Yangyu Tao, Zhi Yang, Bin Cui
Graph neural networks (GNNs) have achieved great success in many graph-based applications.
Ranked #9 on
Node Property Prediction
on ogbn-mag
1 code implementation • 9 Jun 2022 • Wentao Zhang, Zeang Sheng, Ziqi Yin, Yuezihan Jiang, Yikuan Xia, Jun Gao, Zhi Yang, Bin Cui
Graph Neural Networks (GNNs) have achieved great success in various graph mining tasks. However, drastic performance degradation is always observed when a GNN is stacked with many layers.
no code implementations • 6 Jun 2022 • Yang Li, Yu Shen, Huaijun Jiang, Wentao Zhang, Zhi Yang, Ce Zhang, Bin Cui
With the extensive applications of machine learning models, automatic hyperparameter optimization (HPO) has become increasingly important.
no code implementations • 6 Jun 2022 • Yang Li, Yu Shen, Huaijun Jiang, Tianyi Bai, Wentao Zhang, Ce Zhang, Bin Cui
The extensive experiments show that our approach considerably boosts BO by designing a promising and compact search space instead of using the entire space, and outperforms the state-of-the-arts on a wide range of benchmarks, including machine learning and deep learning tuning tasks, and neural architecture search.
no code implementations • 4 Jun 2022 • Yuezihan Jiang, Hao Yang, Junyang Lin, Hanyu Zhao, An Yang, Chang Zhou, Hongxia Yang, Zhi Yang, Bin Cui
Prompt Learning has recently gained great popularity in bridging the gap between pretraining tasks and various downstream tasks.
no code implementations • 25 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.
1 code implementation • 20 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.
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.
1 code implementation • 1 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.
no code implementations • 18 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.
3 code implementations • 29 Dec 2021 • Xiaonan Nie, Xupeng Miao, Shijie Cao, Lingxiao Ma, Qibin Liu, Jilong Xue, Youshan Miao, Yi Liu, Zhi Yang, Bin Cui
Then it diversifies the experts and continues to train the MoE with a novel Dense-to-Sparse gate (DTS-Gate).
no code implementations • 26 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.
2 code implementations • 14 Dec 2021 • Xupeng Miao, Hailin Zhang, Yining Shi, Xiaonan Nie, Zhi Yang, Yangyu Tao, Bin Cui
Embedding models have been an effective learning paradigm for high-dimensional data.
2 code implementations • CVPR 2022 • 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.
Ranked #3 on
Open Vocabulary Object Detection
on STPLS3D
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.
1 code implementation • NeurIPS 2021 • Wentao Zhang, Mingyu Yang, Zeang Sheng, Yang Li, Wen Ouyang, Yangyu Tao, Zhi Yang, Bin Cui
Recent works reveal that feature or label smoothing lies at the core of Graph Neural Networks (GNNs).
no code implementations • 20 Oct 2021 • Yu Shen, Yang Li, Jian Zheng, Wentao Zhang, Peng Yao, Jixiang Li, Sen yang, Ji Liu, Bin Cui
Designing neural architectures requires immense manual efforts.
1 code implementation • 13 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.
no code implementations • 23 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.
1 code implementation • 2 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.
1 code implementation • 31 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.
1 code implementation • 25 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.
3 code implementations • 19 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.
6 code implementations • 1 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.
no code implementations • 28 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.
no code implementations • 20 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.
no code implementations • 28 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.
no code implementations • 8 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.
no code implementations • 7 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.
5 code implementations • 5 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.
1 code implementation • 18 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.
1 code implementation • 4 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.
1 code implementation • 27 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.
1 code implementation • 10 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.
no code implementations • 10 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.
1 code implementation • 25 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.
1 code implementation • 25 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.
no code implementations • 3 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.
no code implementations • 6 Nov 2018 • Yang Li, Jiawei Jiang, Yingxia Shao, Bin Cui
The performance of deep neural networks crucially depends on good hyperparameter configurations.