1 code implementation • 4 Aug 2022 • Hao Yang, Junyang Lin, An Yang, Peng Wang, Chang Zhou, Hongxia Yang
Prompt tuning has become a new paradigm for model tuning and it has demonstrated success in natural language pretraining and even vision pretraining.
Ranked #2 on
Visual Entailment
on SNLI-VE test
1 code implementation • 19 Jul 2022 • Shuai Bai, Huiling Zhou, Zhikang Li, Chang Zhou, Hongxia Yang
Virtual try-on aims to generate a photo-realistic fitting result given an in-shop garment and a reference person image.
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 • 24 May 2022 • Zhikang Li, Huiling Zhou, Shuai Bai, Peike Li, Chang Zhou, Hongxia Yang
The fashion industry has diverse applications in multi-modal image generation and editing.
no code implementations • 17 May 2022 • Zeyu Cui, Jianxin Ma, Chang Zhou, Jingren Zhou, Hongxia Yang
Industrial recommender systems have been growing increasingly complex, may involve \emph{diverse domains} such as e-commerce products and user-generated contents, and can comprise \emph{a myriad of tasks} such as retrieval, ranking, explanation generation, and even AI-assisted content production.
no code implementations • 29 Mar 2022 • Xiao Pan, Peike Li, Zongxin Yang, Huiling Zhou, Chang Zhou, Hongxia Yang, Jingren Zhou, Yi Yang
As to pixel-level optimization, we perform in-view masked image modeling on patch tokens, which recovers the corrupted parts of an image via inferring its fine-grained structure, and we term it as in-generative learning.
no code implementations • 23 Mar 2022 • Yu Huang, Junyang Lin, Chang Zhou, Hongxia Yang, Longbo Huang
Recently, it has been observed that the best uni-modal network outperforms the jointly trained multi-modal network, which is counter-intuitive since multiple signals generally bring more information.
1 code implementation • 7 Feb 2022 • Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, Hongxia Yang
In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization.
Ranked #1 on
Visual Question Answering
on VQA v2 test-std
1 code implementation • 30 Dec 2021 • Qingsong Lv, Ming Ding, Qiang Liu, Yuxiang Chen, Wenzheng Feng, Siming He, Chang Zhou, Jianguo Jiang, Yuxiao Dong, Jie Tang
Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understanding of their advancements.
no code implementations • 8 Oct 2021 • Junyang Lin, An Yang, Jinze Bai, Chang Zhou, Le Jiang, Xianyan Jia, Ang Wang, Jie Zhang, Yong Li, Wei Lin, Jingren Zhou, Hongxia Yang
Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 and Switch Transformer possessing hundreds of billions or even trillions of parameters.
1 code implementation • ICCV 2021 • Tan Wang, Chang Zhou, Qianru Sun, Hanwang Zhang
Attention module does not always help deep models learn causal features that are robust in any confounding context, e. g., a foreground object feature is invariant to different backgrounds.
no code implementations • 8 Jun 2021 • Jingjing Xiong, Lai-Man Po, Wing-Yin Yu, Chang Zhou, Pengfei Xian, Weifeng Ou
Real-time semantic segmentation has received considerable attention due to growing demands in many practical applications, such as autonomous vehicles, robotics, etc.
no code implementations • 2 Jun 2021 • Zhu Zhang, Chang Zhou, Jianxin Ma, Zhijie Lin, Jingren Zhou, Hongxia Yang, Zhou Zhao
Further, we design a history sampler to select informative fragments for rehearsal training, making the memory focus on the crucial information.
no code implementations • 31 May 2021 • An Yang, Junyang Lin, Rui Men, Chang Zhou, Le Jiang, Xianyan Jia, Ang Wang, Jie Zhang, Jiamang Wang, Yong Li, Di Zhang, Wei Lin, Lin Qu, Jingren Zhou, Hongxia Yang
Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scaling.
1 code implementation • 31 May 2021 • Shuai Bai, Zhedong Zheng, Xiaohan Wang, Junyang Lin, Zhu Zhang, Chang Zhou, Yi Yang, Hongxia Yang
In this paper, we apply one new modality, i. e., the language description, to search the vehicle of interest and explore the potential of this task in the real-world scenario.
1 code implementation • 31 May 2021 • Haonan Wang, Chang Zhou, Carl Yang, Hongxia Yang, Jingrui He
A better way is to present a sequence of products with increasingly floral attributes based on the white dress, and allow the customer to select the most satisfactory one from the sequence.
no code implementations • Findings (ACL) 2021 • Peng Wang, Junyang Lin, An Yang, Chang Zhou, Yichang Zhang, Jingren Zhou, Hongxia Yang
Experimental results demonstrate that our method outperforms the previous state-of-the-art methods in both automatic and human evaluation, especially on coverage and faithfulness.
no code implementations • NeurIPS 2021 • Zhu Zhang, Jianxin Ma, Chang Zhou, Rui Men, Zhikang Li, Ming Ding, Jie Tang, Jingren Zhou, Hongxia Yang
Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations.
3 code implementations • NeurIPS 2021 • Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, Jie Tang
Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding.
Ranked #22 on
Text-to-Image Generation
on COCO
(using extra training data)
no code implementations • NeurIPS 2021 • Zhu Zhang, Jianxin Ma, Chang Zhou, Rui Men, Zhikang Li, Ming Ding, Jie Tang, Jingren Zhou, Hongxia Yang
Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations.
1 code implementation • 1 Mar 2021 • Yukuo Cen, Zhenyu Hou, Yan Wang, Qibin Chen, Yizhen Luo, Zhongming Yu, Hengrui Zhang, Xingcheng Yao, Aohan Zeng, Shiguang Guo, Yuxiao Dong, Yang Yang, Peng Zhang, Guohao Dai, Yu Wang, Chang Zhou, Hongxia Yang, Jie Tang
Deep learning on graphs has attracted tremendous attention from the graph learning community in recent years.
no code implementations • 1 Mar 2021 • Junyang Lin, Rui Men, An Yang, Chang Zhou, Ming Ding, Yichang Zhang, Peng Wang, Ang Wang, Le Jiang, Xianyan Jia, Jie Zhang, Jianwei Zhang, Xu Zou, Zhikang Li, Xiaodong Deng, Jie Liu, Jinbao Xue, Huiling Zhou, Jianxin Ma, Jin Yu, Yong Li, Wei Lin, Jingren Zhou, Jie Tang, Hongxia Yang
In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1. 9TB images and 292GB texts that cover a wide range of domains.
no code implementations • 1 Jan 2021 • Jiezhong Qiu, Yukuo Cen, Qibin Chen, Chang Zhou, Jingren Zhou, Hongxia Yang, Jie Tang
Based on the theoretical analysis, we propose Local Clustering Graph Neural Networks (LCGNN), a GNN learning paradigm that utilizes local clustering to efficiently search for small but compact subgraphs for GNN training and inference.
no code implementations • 1 Jan 2021 • Zhu Zhang, Chang Zhou, Zhou Zhao, Zhijie Lin, Jingren Zhou, Hongxia Yang
Existing reasoning tasks often follow the setting of "reasoning while experiencing", which has an important assumption that the raw contents can be always accessed while reasoning.
no code implementations • 1 Jan 2021 • Yue Wu, Jianqiang Huang, Jiangjie Zhen, Guokun Wang, Chen Shen, Chang Zhou, Xian-Sheng Hua
The past years have witnessed an explosion of deep learning frameworks like PyTorch and TensorFlow since the success of deep neural networks.
1 code implementation • NeurIPS 2020 • Ming Ding, Chang Zhou, Hongxia Yang, Jie Tang
BERTs are incapable of processing long texts due to its quadratically increasing memory and time consumption.
1 code implementation • 23 Aug 2020 • Jianxin Ma, Chang Zhou, Hongxia Yang, Peng Cui, Xin Wang, Wenwu Zhu
There exist two challenges: i) reconstructing a future sequence containing many behaviors is exponentially harder than reconstructing a single next behavior, which can lead to difficulty in convergence, and ii) the sequence of all future behaviors can involve many intentions, not all of which may be predictable from the sequence of earlier behaviors.
no code implementations • 20 May 2020 • Chang Zhou, Jianxin Ma, Jianwei Zhang, Jingren Zhou, Hongxia Yang
Deep candidate generation (DCG) that narrows down the collection of relevant items from billions to hundreds via representation learning has become prevalent in industrial recommender systems.
2 code implementations • 20 May 2020 • Zhen Yang, Ming Ding, Chang Zhou, Hongxia Yang, Jingren Zhou, Jie Tang
To the best of our knowledge, we are the first to derive the theory and quantify that the negative sampling distribution should be positively but sub-linearly correlated to their positive sampling distribution.
2 code implementations • 19 May 2020 • Yukuo Cen, Jianwei Zhang, Xu Zou, Chang Zhou, Hongxia Yang, Jie Tang
Recent works usually give an overall embedding from a user's behavior sequence.
no code implementations • ICLR 2020 • Baichuan Yuan, Xiaowei Wang, Jianxin Ma, Chang Zhou, Andrea L. Bertozzi, Hongxia Yang
To bridge this gap, we introduce a declustering based hidden variable model that leads to an efficient inference procedure via a variational autoencoder (VAE).
no code implementations • 2 Dec 2019 • Chunnan Wang, Hongzhi Wang, Chang Zhou, Hanxiao Chen
Motivated by this, we propose ExperienceThinking algorithm to quickly find the best possible hyperparameter configuration of machine learning algorithms within a few configuration evaluations.
no code implementations • NeurIPS 2019 • Jianxin Ma, Chang Zhou, Peng Cui, Hongxia Yang, Wenwu Zhu
Our approach achieves macro disentanglement by inferring the high-level concepts associated with user intentions (e. g., to buy a shirt or a cellphone), while capturing the preference of a user regarding the different concepts separately.
no code implementations • 25 Sep 2019 • Xu Zou, Qiuye Jia, Jianwei Zhang, Chang Zhou, Zijun Yao, Hongxia Yang, Jie Tang
In this paper, we propose a method named Dimensional reweighting Graph Convolutional Networks (DrGCNs), to tackle the problem of variance between dimensional information in the node representations of GCNs.
2 code implementations • 4 Jul 2019 • Xu Zou, Qiuye Jia, Jianwei Zhang, Chang Zhou, Hongxia Yang, Jie Tang
Graph Convolution Networks (GCNs) are becoming more and more popular for learning node representations on graphs.
1 code implementation • 13 Jun 2019 • Zhengxiao Du, Chang Zhou, Ming Ding, Hongxia Yang, Jie Tang
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently.
3 code implementations • ACL 2019 • Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, Jie Tang
We propose a new CogQA framework for multi-hop question answering in web-scale documents.
Ranked #53 on
Question Answering
on HotpotQA
Multi-hop Question Answering
Multi-Hop Reading Comprehension
+1
no code implementations • 3 Apr 2019 • Jinze Bai, Chang Zhou, Junshuai Song, Xiaoru Qu, Weiting An, Zhao Li, Jun Gao
In particular, BGN improves the precision of the best competitors by 16\% on average while maintaining the highest diversity on four datasets, and yields a 3. 85x improvement of response time over the best competitors in the bundle list recommendation problem.
no code implementations • 23 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
13 code implementations • 11 Sep 2018 • Guorui Zhou, Na Mou, Ying Fan, Qi Pi, Weijie Bian, Chang Zhou, Xiaoqiang Zhu, Kun Gai
Easy-to-use, Modular and Extendible package of deep-learning based CTR models. DeepFM, DeepInterestNetwork(DIN), DeepInterestEvolutionNetwork(DIEN), DeepCrossNetwork(DCN), AttentionalFactorizationMachine(AFM), Neural Factorization Machine(NFM), AutoInt
Ranked #1 on
Click-Through Rate Prediction
on Amazon Dataset
2 code implementations • 17 Nov 2017 • Chang Zhou, Jinze Bai, Junshuai Song, Xiaofei Liu, Zhengchao Zhao, Xiusi Chen, Jun Gao
Downstream applications then can use the user behavior vectors via vanilla attention.