Search Results for author: Shengyu Zhang

Found 57 papers, 22 papers with code

Instruction Tuning for Large Language Models: A Survey

1 code implementation21 Aug 2023 Shengyu Zhang, Linfeng Dong, Xiaoya Li, Sen Zhang, Xiaofei Sun, Shuhe Wang, Jiwei Li, Runyi Hu, Tianwei Zhang, Fei Wu, Guoyin Wang

In this work, we make a systematic review of the literature, including the general methodology of IT, the construction of IT datasets, the training of IT models, and applications to different modalities, domains and applications, along with an analysis on aspects that influence the outcome of IT (e. g., generation of instruction outputs, size of the instruction dataset, etc).

DisCover: Disentangled Music Representation Learning for Cover Song Identification

no code implementations19 Jul 2023 Jiahao Xun, Shengyu Zhang, Yanting Yang, Jieming Zhu, Liqun Deng, Zhou Zhao, Zhenhua Dong, RuiQi Li, Lichao Zhang, Fei Wu

We analyze the CSI task in a disentanglement view with the causal graph technique, and identify the intra-version and inter-version effects biasing the invariant learning.

Blocking Cover song identification +3

Multi-task Bioassay Pre-training for Protein-ligand Binding Affinity Prediction

no code implementations8 Jun 2023 Jiaxian Yan, Zhaofeng Ye, ZiYi Yang, Chengqiang Lu, Shengyu Zhang, Qi Liu, Jiezhong Qiu

By introducing multi-task pre-training to treat the prediction of different affinity labels as different tasks and classifying relative rankings between samples from the same bioassay, MBP learns robust and transferrable structural knowledge from our new ChEMBL-Dock dataset with varied and noisy labels.

Drug Discovery

Denoising Multi-modal Sequential Recommenders with Contrastive Learning

no code implementations3 May 2023 Dong Yao, Shengyu Zhang, Zhou Zhao, Jieming Zhu, Wenqiao Zhang, Rui Zhang, Xiaofei He, Fei Wu

In contrast, modalities that do not cause users' behaviors are potential noises and might mislead the learning of a recommendation model.

Contrastive Learning Denoising +2

Error-mitigated Quantum Approximate Optimization via Learning-based Adaptive Optimization

2 code implementations27 Mar 2023 Lixue Cheng, Yu-Qin Chen, Shi-Xin Zhang, Shengyu Zhang

Quantum approximate optimization algorithm (QAOA), one of the most representative quantum-classical hybrid algorithms, is designed to solve certain combinatorial optimization problems by transforming a discrete optimization problem into a classical optimization problem over a continuous circuit parameter domain.

Bayesian Optimization Combinatorial Optimization

IDEAL: Toward High-efficiency Device-Cloud Collaborative and Dynamic Recommendation System

no code implementations14 Feb 2023 Zheqi Lv, Zhengyu Chen, Shengyu Zhang, Kun Kuang, Wenqiao Zhang, Mengze Li, Beng Chin Ooi, Fei Wu

The aforementioned two trends enable the device-cloud collaborative and dynamic recommendation, which deeply exploits the recommendation pattern among cloud-device data and efficiently characterizes different instances with different underlying distributions based on the cost of frequent device-cloud communication.

Recommendation Systems Vocal Bursts Intensity Prediction

Multi-Constraint Molecular Generation using Sparsely Labelled Training Data for Localized High-Concentration Electrolyte Diluent Screening

no code implementations12 Jan 2023 Jonathan P. Mailoa, Xin Li, Jiezhong Qiu, Shengyu Zhang

Recently, machine learning methods have been used to propose molecules with desired properties, which is especially useful for exploring large chemical spaces efficiently.

Protein-Ligand Complex Generator & Drug Screening via Tiered Tensor Transform

1 code implementation3 Jan 2023 Jonathan P. Mailoa, Zhaofeng Ye, Jiezhong Qiu, Chang-Yu Hsieh, Shengyu Zhang

The generation of small molecule candidate (ligand) binding poses in its target protein pocket is important for computer-aided drug discovery.

Drug Discovery

Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning

1 code implementation CVPR 2023 Wei Ji, Renjie Liang, Zhedong Zheng, Wenqiao Zhang, Shengyu Zhang, Juncheng Li, Mengze Li, Tat-Seng Chua

Moreover, we treat the uncertainty score of frames in a video as a whole, and estimate the difficulty of each video, which can further relieve the burden of video selection.

Active Learning Moment Retrieval +1

WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding

no code implementations CVPR 2023 Mengze Li, Han Wang, Wenqiao Zhang, Jiaxu Miao, Zhou Zhao, Shengyu Zhang, Wei Ji, Fei Wu

WINNER first builds the language decomposition tree in a bottom-up manner, upon which the structural attention mechanism and top-down feature backtracking jointly build a multi-modal decomposition tree, permitting a hierarchical understanding of unstructured videos.

Contrastive Learning Spatio-Temporal Video Grounding +1

DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization

1 code implementation12 Sep 2022 Zheqi Lv, Wenqiao Zhang, Shengyu Zhang, Kun Kuang, Feng Wang, Yongwei Wang, Zhengyu Chen, Tao Shen, Hongxia Yang, Beng Chin Ooi, Fei Wu

DUET is deployed on a powerful cloud server that only requires the low cost of forwarding propagation and low time delay of data transmission between the device and the cloud.

Device-Cloud Collaboration Domain Adaptation +3

Personalizing Intervened Network for Long-tailed Sequential User Behavior Modeling

no code implementations19 Aug 2022 Zheqi Lv, Feng Wang, Shengyu Zhang, Kun Kuang, Hongxia Yang, Fei Wu

In this paper, we propose a novel approach that significantly improves the recommendation performance of the tail users while achieving at least comparable performance for the head users over the base model.

Recommendation Systems

CCL4Rec: Contrast over Contrastive Learning for Micro-video Recommendation

no code implementations17 Aug 2022 Shengyu Zhang, Bofang Li, Dong Yao, Fuli Feng, Jieming Zhu, Wenyan Fan, Zhou Zhao, Xiaofei He, Tat-Seng Chua, Fei Wu

Micro-video recommender systems suffer from the ubiquitous noises in users' behaviors, which might render the learned user representation indiscriminating, and lead to trivial recommendations (e. g., popular items) or even weird ones that are far beyond users' interests.

Contrastive Learning Recommendation Systems

Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation

1 code implementation17 Aug 2022 Shengyu Zhang, Lingxiao Yang, Dong Yao, Yujie Lu, Fuli Feng, Zhou Zhao, Tat-Seng Chua, Fei Wu

Specifically, Re4 encapsulates three backward flows, i. e., 1) Re-contrast, which drives each interest embedding to be distinct from other interests using contrastive learning; 2) Re-attend, which ensures the interest-item correlation estimation in the forward flow to be consistent with the criterion used in final recommendation; and 3) Re-construct, which ensures that each interest embedding can semantically reflect the information of representative items that relate to the corresponding interest.

Contrastive Learning Recommendation Systems

Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos

1 code implementation3 Aug 2022 Juncheng Li, Junlin Xie, Linchao Zhu, Long Qian, Siliang Tang, Wenqiao Zhang, Haochen Shi, Shengyu Zhang, Longhui Wei, Qi Tian, Yueting Zhuang

In this paper, we introduce a new task, named Temporal Emotion Localization in videos~(TEL), which aims to detect human emotions and localize their corresponding temporal boundaries in untrimmed videos with aligned subtitles.

Emotion Classification Temporal Action Localization +1

BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrieval

no code implementations9 Jul 2022 Wenqiao Zhang, Jiannan Guo, Mengze Li, Haochen Shi, Shengyu Zhang, Juncheng Li, Siliang Tang, Yueting Zhuang

In this scenario, the input image serves as an intuitive context and background for the search, while the corresponding language expressly requests new traits on how specific characteristics of the query image should be modified in order to get the intended target image.

Content-Based Image Retrieval Retrieval +1

An adaptive graph learning method for automated molecular interactions and properties predictions

1 code implementation Nature Machine Intelligence 2022 Yuquan Li, Chang-Yu Hsieh, Ruiqiang Lu, Xiaoqing Gong, Xiaorui Wang, Pengyong Li, Shuo Liu, Yanan Tian, Dejun Jiang, Jiaxian Yan, Qifeng Bai, Huanxiang Liu, Shengyu Zhang, Xiaojun Yao

In fact, the pursuit of high prediction performance on a limited number of datasets has crystallized their architectures and hyperparameters, making them lose advantage in repurposing to new data generated in drug discovery.

Drug Discovery Graph Learning +2

Intelligent Request Strategy Design in Recommender System

no code implementations23 Jun 2022 Xufeng Qian, Yue Xu, Fuyu Lv, Shengyu Zhang, Ziwen Jiang, Qingwen Liu, Xiaoyi Zeng, Tat-Seng Chua, Fei Wu

RSs typically put a large number of items into one page to reduce excessive resource consumption from numerous paging requests, which, however, would diminish the RSs' ability to timely renew the recommendations according to users' real-time interest and lead to a poor user experience.

Causal Inference Recommendation Systems

ODBO: Bayesian Optimization with Search Space Prescreening for Directed Protein Evolution

2 code implementations19 May 2022 Lixue Cheng, ZiYi Yang, ChangYu Hsieh, Benben Liao, Shengyu Zhang

Directed evolution is a versatile technique in protein engineering that mimics the process of natural selection by iteratively alternating between mutagenesis and screening in order to search for sequences that optimize a given property of interest, such as catalytic activity and binding affinity to a specified target.

Bayesian Optimization Experimental Design +1

Contrastive Learning with Positive-Negative Frame Mask for Music Representation

no code implementations17 Mar 2022 Dong Yao, Zhou Zhao, Shengyu Zhang, Jieming Zhu, Yudong Zhu, Rui Zhang, Xiuqiang He

We devise a novel contrastive learning objective to accommodate both self-augmented positives/negatives sampled from the same music.

Contrastive Learning Cover song identification +2

End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding

no code implementations ACL 2022 Mengze Li, Tianbao Wang, Haoyu Zhang, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Wenming Tan, Jin Wang, Peng Wang, ShiLiang Pu, Fei Wu

To achieve effective grounding under a limited annotation budget, we investigate one-shot video grounding, and learn to ground natural language in all video frames with solely one frame labeled, in an end-to-end manner.

Descriptive Representation Learning +1

BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation

1 code implementation CVPR 2022 Wenqiao Zhang, Lei Zhu, James Hallinan, Andrew Makmur, Shengyu Zhang, Qingpeng Cai, Beng Chin Ooi

In this paper, we propose a novel semi-supervised learning (SSL) framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models: (1) BoostMIS can adaptively leverage the cluster assumption and consistency regularization of the unlabeled data according to the current learning status.

Active Learning

A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation

no code implementations21 Feb 2022 Dongqi Wang, Shengyu Zhang, Zhipeng Di, Xin Lin, Weihua Zhou, Fei Wu

A common problem in both pruning and distillation is to determine compressed architecture, i. e., the exact number of filters per layer and layer configuration, in order to preserve most of the original model capacity.

Knowledge Distillation Model Compression +1

Retroformer: Pushing the Limits of Interpretable End-to-end Retrosynthesis Transformer

1 code implementation29 Jan 2022 Yue Wan, Benben Liao, Chang-Yu Hsieh, Shengyu Zhang

In this paper, we propose Retroformer, a novel Transformer-based architecture for retrosynthesis prediction without relying on any cheminformatics tools for molecule editing.


SPLDExtraTrees: Robust machine learning approach for predicting kinase inhibitor resistance

no code implementations15 Nov 2021 ZiYi Yang, Zhaofeng Ye, Yijia Xiao, ChangYu Hsieh, Shengyu Zhang

Drug resistance is a major threat to the global health and a significant concern throughout the clinical treatment of diseases and drug development.

BIG-bench Machine Learning

Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI

1 code implementation11 Nov 2021 Jiangchao Yao, Shengyu Zhang, Yang Yao, Feng Wang, Jianxin Ma, Jianwei Zhang, Yunfei Chu, Luo Ji, Kunyang Jia, Tao Shen, Anpeng Wu, Fengda Zhang, Ziqi Tan, Kun Kuang, Chao Wu, Fei Wu, Jingren Zhou, Hongxia Yang

However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed.

Cloud Computing Edge-computing

MIC: Model-agnostic Integrated Cross-channel Recommenders

no code implementations22 Oct 2021 Yujie Lu, Ping Nie, Shengyu Zhang, Ming Zhao, Ruobing Xie, William Yang Wang, Yi Ren

However, existing work are primarily built upon pre-defined retrieval channels, including User-CF (U2U), Item-CF (I2I), and Embedding-based Retrieval (U2I), thus access to the limited correlation between users and items which solely entail from partial information of latent interactions.

Recommendation Systems Retrieval +2

Multi-trends Enhanced Dynamic Micro-video Recommendation

no code implementations8 Oct 2021 Yujie Lu, Yingxuan Huang, Shengyu Zhang, Wei Han, Hui Chen, Zhou Zhao, Fei Wu

In this paper, we propose the DMR framework to explicitly model dynamic multi-trends of users' current preference and make predictions based on both the history and future potential trends.

Recommendation Systems

Stable Prediction on Graphs with Agnostic Distribution Shift

no code implementations8 Oct 2021 Shengyu Zhang, Kun Kuang, Jiezhong Qiu, Jin Yu, Zhou Zhao, Hongxia Yang, Zhongfei Zhang, Fei Wu

The results demonstrate that our method outperforms various SOTA GNNs for stable prediction on graphs with agnostic distribution shift, including shift caused by node labels and attributes.

Graph Learning Recommendation Systems

Why Do We Click: Visual Impression-aware News Recommendation

1 code implementation26 Sep 2021 Jiahao Xun, Shengyu Zhang, Zhou Zhao, Jieming Zhu, Qi Zhang, Jingjie Li, Xiuqiang He, Xiaofei He, Tat-Seng Chua, Fei Wu

In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation.

Decision Making News Recommendation

Fast Extraction of Word Embedding from Q-contexts

no code implementations15 Sep 2021 Junsheng Kong, Weizhao Li, Zeyi Liu, Ben Liao, Jiezhong Qiu, Chang-Yu Hsieh, Yi Cai, Shengyu Zhang

In this work, we show that with merely a small fraction of contexts (Q-contexts)which are typical in the whole corpus (and their mutual information with words), one can construct high-quality word embedding with negligible errors.

CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation

no code implementations11 Sep 2021 Shengyu Zhang, Dong Yao, Zhou Zhao, Tat-Seng Chua, Fei Wu

In this paper, we propose to learn accurate and robust user representations, which are required to be less sensitive to (attack on) noisy behaviors and trust more on the indispensable ones, by modeling counterfactual data distribution.

Representation Learning Sequential Recommendation

Neural Predictor based Quantum Architecture Search

no code implementations11 Mar 2021 Shi-Xin Zhang, Chang-Yu Hsieh, Shengyu Zhang, Hong Yao

For instance, a key component of VQAs is the design of task-dependent parameterized quantum circuits (PQCs) as in the case of designing a good neural architecture in deep learning.

Neural Architecture Search Quantum Physics

TrimNet: learning molecular representation from triplet messages for biomedicine

1 code implementation4 Nov 2020 Pengyong Li, Yuquan Li, Chang-Yu Hsieh, Shengyu Zhang, Xianggen Liu, Huanxiang Liu, Sen Song, Xiaojun Yao

These advantages have established TrimNet as a powerful and useful computational tool in solving the challenging problem of molecular representation learning.

Drug Discovery Molecular Property Prediction +3

Future-Aware Diverse Trends Framework for Recommendation

1 code implementation1 Nov 2020 Yujie Lu, Shengyu Zhang, Yingxuan Huang, Luyao Wang, Xinyao Yu, Zhou Zhao, Fei Wu

By diverse trends, supposing the future preferences can be diversified, we propose the diverse trends extractor and the time-aware mechanism to represent the possible trends of preferences for a given user with multiple vectors.

Representation Learning Sequential Recommendation

Differentiable Quantum Architecture Search

1 code implementation16 Oct 2020 Shi-Xin Zhang, Chang-Yu Hsieh, Shengyu Zhang, Hong Yao

Hereby, we propose a general framework of differentiable quantum architecture search (DQAS), which enables automated designs of quantum circuits in an end-to-end differentiable fashion.

Quantum Physics

MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination

no code implementations2 Oct 2020 Shengyu Zhang, Donghui Wang, Zhou Zhao, Siliang Tang, Di Xie, Fei Wu

In this paper, we investigate the problem of text-to-pedestrian synthesis, which has many potential applications in art, design, and video surveillance.

Image Generation

DeVLBert: Learning Deconfounded Visio-Linguistic Representations

1 code implementation16 Aug 2020 Shengyu Zhang, Tan Jiang, Tan Wang, Kun Kuang, Zhou Zhao, Jianke Zhu, Jin Yu, Hongxia Yang, Fei Wu

In this paper, we propose to investigate the problem of out-of-domain visio-linguistic pretraining, where the pretraining data distribution differs from that of downstream data on which the pretrained model will be fine-tuned.

Image Retrieval Question Answering +2

Poet: Product-oriented Video Captioner for E-commerce

1 code implementation16 Aug 2020 Shengyu Zhang, Ziqi Tan, Jin Yu, Zhou Zhao, Kun Kuang, Jie Liu, Jingren Zhou, Hongxia Yang, Fei Wu

Then, based on the aspects of the video-associated product, we perform knowledge-enhanced spatial-temporal inference on those graphs for capturing the dynamic change of fine-grained product-part characteristics.

Video Captioning

Comprehensive Information Integration Modeling Framework for Video Titling

1 code implementation24 Jun 2020 Shengyu Zhang, Ziqi Tan, Jin Yu, Zhou Zhao, Kun Kuang, Tan Jiang, Jingren Zhou, Hongxia Yang, Fei Wu

In e-commerce, consumer-generated videos, which in general deliver consumers' individual preferences for the different aspects of certain products, are massive in volume.

Descriptive Video Captioning

Adaptive Double-Exploration Tradeoff for Outlier Detection

no code implementations13 May 2020 Xiaojin Zhang, Honglei Zhuang, Shengyu Zhang, Yuan Zhou

We study a variant of the thresholding bandit problem (TBP) in the context of outlier detection, where the objective is to identify the outliers whose rewards are above a threshold.

Outlier Detection

Grounded and Controllable Image Completion by Incorporating Lexical Semantics

no code implementations29 Feb 2020 Shengyu Zhang, Tan Jiang, Qinghao Huang, Ziqi Tan, Zhou Zhao, Siliang Tang, Jin Yu, Hongxia Yang, Yi Yang, Fei Wu

Existing image completion procedure is highly subjective by considering only visual context, which may trigger unpredictable results which are plausible but not faithful to a grounded knowledge.

Contextual Combinatorial Conservative Bandits

no code implementations26 Nov 2019 Xiaojin Zhang, Shuai Li, Weiwen Liu, Shengyu Zhang

The problem of multi-armed bandits (MAB) asks to make sequential decisions while balancing between exploitation and exploration, and have been successfully applied to a wide range of practical scenarios.

Multi-Armed Bandits

DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow

no code implementations30 Oct 2019 Xiang Pan, Tianyu Zhao, Minghua Chen, Shengyu Zhang

We then directly reconstruct the phase angles from the generations and loads by using the power flow equations.

A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR

no code implementations13 Jun 2019 Pengfei Chen, Benben Liao, Guangyong Chen, Shengyu Zhang

Most recent efforts have been devoted to defending noisy labels by discarding noisy samples from the training set or assigning weights to training samples, where the weight associated with a noisy sample is expected to be small.

Data Augmentation

Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization

no code implementations13 Jun 2019 Pengfei Chen, Weiwen Liu, Chang-Yu Hsieh, Guangyong Chen, Shengyu Zhang

The IGNN model is based on an elegant and fundamental idea in information theory as explained in the main text, and it could be easily generalized beyond the contexts of molecular graphs considered in this work.

Drug Discovery Quantum Chemistry Regression

Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks

1 code implementation15 May 2019 Guangyong Chen, Pengfei Chen, Yujun Shi, Chang-Yu Hsieh, Benben Liao, Shengyu Zhang

Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed.

Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels

2 code implementations13 May 2019 Pengfei Chen, Benben Liao, Guangyong Chen, Shengyu Zhang

Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the noisy labels.

Image Classification

Quantum algorithms for feedforward neural networks

no code implementations7 Dec 2018 Jonathan Allcock, Chang-Yu Hsieh, Iordanis Kerenidis, Shengyu Zhang

The running times of our algorithms can be quadratically faster in the size of the network than their standard classical counterparts since they depend linearly on the number of neurons in the network, as opposed to the number of connections between neurons as in the classical case.

BIG-bench Machine Learning Quantum Machine Learning +1

Log Hyperbolic Cosine Loss Improves Variational Auto-Encoder

no code implementations27 Sep 2018 Pengfei Chen, Guangyong Chen, Shengyu Zhang

In Variational Auto-Encoder (VAE), the default choice of reconstruction loss function between the decoded sample and the input is the squared $L_2$.

Learning to Aggregate Ordinal Labels by Maximizing Separating Width

no code implementations ICML 2017 Guangyong Chen, Shengyu Zhang, Di Lin, Hui Huang, Pheng Ann Heng

While crowdsourcing has been a cost and time efficient method to label massive samples, one critical issue is quality control, for which the key challenge is to infer the ground truth from noisy or even adversarial data by various users.

Networked Fairness in Cake Cutting

no code implementations7 Jul 2017 Xiaohui Bei, Youming Qiao, Shengyu Zhang

We introduce a graphical framework for fair division in cake cutting, where comparisons between agents are limited by an underlying network structure.


On the Complexity of Trial and Error

no code implementations6 May 2012 Xiaohui Bei, Ning Chen, Shengyu Zhang

On one hand, despite the seemingly very little information provided by the verification oracle, efficient algorithms do exist for a number of important problems.

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