Search Results for author: Xiaolin Zheng

Found 39 papers, 4 papers with code

Personalized Behavior-Aware Transformer for Multi-Behavior Sequential Recommendation

1 code implementation22 Feb 2024 Jiajie Su, Chaochao Chen, Zibin Lin, Xi Li, Weiming Liu, Xiaolin Zheng

To tackle these challenges, we propose a Personalized Behavior-Aware Transformer framework (PBAT) for MBSR problem, which models personalized patterns and multifaceted sequential collaborations in a novel way to boost recommendation performance.

Sequential Recommendation

Learning Uniform Clusters on Hypersphere for Deep Graph-level Clustering

no code implementations23 Nov 2023 Mengling Hu, Chaochao Chen, Weiming Liu, Xinyi Zhang, Xinting Liao, Xiaolin Zheng

However, most existing graph clustering methods focus on node-level clustering, i. e., grouping nodes in a single graph into clusters.

Clustering Contrastive Learning +2

Federated Learning for Short Text Clustering

no code implementations23 Nov 2023 Mengling Hu, Chaochao Chen, Weiming Liu, Xinting Liao, Xiaolin Zheng

The robust short text clustering module aims to train an effective short text clustering model with local data in each client.

Clustering Federated Learning +1

Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems

no code implementations6 Oct 2023 Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Yizhao Zhang, Zhongxuan Han, Dan Meng, Jun Wang

To address the PoT-AU problem in recommender systems, we design a two-component loss function that consists of i) distinguishability loss: making attribute labels indistinguishable from attackers, and ii) regularization loss: preventing drastic changes in the model that result in a negative impact on recommendation performance.

Attribute Recommendation Systems

In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems

no code implementations4 Sep 2023 Zhongxuan Han, Chaochao Chen, Xiaolin Zheng, Weiming Liu, Jun Wang, Wenjie Cheng, Yuyuan Li

By combining the fairness loss with the original backbone model loss, we address the UOF issue and maintain the overall recommendation performance simultaneously.

Fairness Recommendation Systems

Defending Label Inference Attacks in Split Learning under Regression Setting

no code implementations18 Aug 2023 Haoze Qiu, Fei Zheng, Chaochao Chen, Xiaolin Zheng

As a privacy-preserving method for implementing Vertical Federated Learning, Split Learning has been extensively researched.

Federated Learning Privacy Preserving +1

Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data

no code implementations17 Aug 2023 Xinting Liao, Chaochao Chen, Weiming Liu, Pengyang Zhou, Huabin Zhu, Shuheng Shen, Weiqiang Wang, Mengling Hu, Yanchao Tan, Xiaolin Zheng

In server, GNE reaches an agreement among inconsistent and discrepant model deviations from clients to server, which encourages the global model to update in the direction of global optimum without breaking down the clients optimization toward their local optimums.

Federated Learning

Freshness or Accuracy, Why Not Both? Addressing Delayed Feedback via Dynamic Graph Neural Networks

no code implementations15 Aug 2023 Xiaolin Zheng, Zhongyu Wang, Chaochao Chen, Feng Zhu, Jiashu Qian

In the model training, we propose a novel graph convolutional method named HLGCN, which leverages both high-pass and low-pass filters to deal with conversion and non-conversion relationships.

Federated Large Language Model: A Position Paper

no code implementations18 Jul 2023 Chaochao Chen, Xiaohua Feng, Jun Zhou, Jianwei Yin, Xiaolin Zheng

Large scale language models (LLM) have received significant attention and found diverse applications across various domains, but their development encounters challenges in real-world scenarios.

Federated Learning Language Modelling +3

Federated Unlearning via Active Forgetting

no code implementations7 Jul 2023 Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Jiaming Zhang

To this end, we propose a novel federated unlearning framework based on incremental learning, which is independent of specific models and federated settings.

Federated Learning Incremental Learning +1

PPGenCDR: A Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation

no code implementations11 May 2023 Xinting Liao, Weiming Liu, Xiaolin Zheng, Binhui Yao, Chaochao Chen

Privacy-preserving cross-domain recommendation (PPCDR) refers to preserving the privacy of users when transferring the knowledge from source domain to target domain for better performance, which is vital for the long-term development of recommender systems.

Generative Adversarial Network Privacy Preserving +1

Selective and Collaborative Influence Function for Efficient Recommendation Unlearning

no code implementations20 Apr 2023 Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Yizhao Zhang, Biao Gong, Jun Wang

In this paper, we first identify two main disadvantages of directly applying existing unlearning methods in the context of recommendation, i. e., (i) unsatisfactory efficiency for large-scale recommendation models and (ii) destruction of collaboration across users and items.

Recommendation Systems

Heterogeneous Information Crossing on Graphs for Session-based Recommender Systems

no code implementations24 Oct 2022 Xiaolin Zheng, Rui Wu, Zhongxuan Han, Chaochao Chen, Linxun Chen, Bing Han

HICG utilizes multiple types of user behaviors in the sessions to construct heterogeneous graphs, and captures users' current interests with their long-term preferences by effectively crossing the heterogeneous information on the graphs.

Contrastive Learning Recommendation Systems

Making Split Learning Resilient to Label Leakage by Potential Energy Loss

no code implementations18 Oct 2022 Fei Zheng, Chaochao Chen, Binhui Yao, Xiaolin Zheng

As a practical privacy-preserving learning method, split learning has drawn much attention in academia and industry.

Privacy Preserving

DDGHM: Dual Dynamic Graph with Hybrid Metric Training for Cross-Domain Sequential Recommendation

no code implementations21 Sep 2022 Xiaolin Zheng, Jiajie Su, Weiming Liu, Chaochao Chen

However, the short interaction sequences limit the performance of existing SR. To solve this problem, we focus on Cross-Domain Sequential Recommendation (CDSR) in this paper, which aims to leverage information from other domains to improve the sequential recommendation performance of a single domain.

Metric Learning Sequential Recommendation

Exploiting Variational Domain-Invariant User Embedding for Partially Overlapped Cross Domain Recommendation

no code implementations13 May 2022 Weiming Liu, Xiaolin Zheng, Mengling Hu, Chaochao Chen

Most of the existing CDR models assume that both the source and target domains share the same overlapped user set for knowledge transfer.

Recommendation Systems Transfer Learning +1

Partial Relaxed Optimal Transport for Denoised Recommendation

no code implementations19 Apr 2022 Yanchao Tan, Carl Yang Member, Xiangyu Wei, Ziyue Wu, Xiaolin Zheng

The interaction data used by recommender systems (RSs) inevitably include noises resulting from mistaken or exploratory clicks, especially under implicit feedbacks.

Denoising Recommendation Systems

Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation

no code implementations22 Mar 2022 Yuyuan Li, Xiaolin Zheng, Chaochao Chen, Junlin Liu

The basic idea of most recommender systems is collaborative filtering, but existing MU methods ignore the collaborative information across users and items.

Collaborative Filtering Machine Unlearning +1

Differential Private Knowledge Transfer for Privacy-Preserving Cross-Domain Recommendation

no code implementations10 Feb 2022 Chaochao Chen, Huiwen Wu, Jiajie Su, Lingjuan Lyu, Xiaolin Zheng, Li Wang

To this end, PriCDR can not only protect the data privacy of the source domain, but also alleviate the data sparsity of the source domain.

Privacy Preserving Recommendation Systems +1

Leveraging Distribution Alignment via Stein Path for Cross-Domain Cold-Start Recommendation

no code implementations NeurIPS 2021 Weiming Liu, Jiajie Su, Chaochao Chen, Xiaolin Zheng

To address this issue, we propose DisAlign, a cross-domain recommendation framework for the CDCSR problem, which utilizes both rating and auxiliary representations from the source domain to improve the recommendation performance of the target domain.

Recommendation Systems

Towards Secure and Practical Machine Learning via Secret Sharing and Random Permutation

1 code implementation17 Aug 2021 Fei Zheng, Chaochao Chen, Xiaolin Zheng, Mingjie Zhu

Since our method reduces the cost for element-wise function computation, it is more efficient than existing cryptographic methods.

BIG-bench Machine Learning Privacy Preserving +1

Multi-Facet Recommender Networks with Spherical Optimization

1 code implementation27 Mar 2021 Yanchao Tan, Carl Yang, Xiangyu Wei, Yun Ma, Xiaolin Zheng

Metric learning has been proposed to capture user-item interactions from implicit feedback, but existing methods only represent users and items in a single metric space, ignoring the fact that users can have multiple preferences and items can have multiple properties, which leads to potential conflicts limiting their performance in recommendation.

Metric Learning Recommendation Systems +1

Towards Scalable and Privacy-Preserving Deep Neural Network via Algorithmic-Cryptographic Co-design

no code implementations17 Dec 2020 Jun Zhou, Longfei Zheng, Chaochao Chen, Yan Wang, Xiaolin Zheng, Bingzhe Wu, Cen Chen, Li Wang, Jianwei Yin

In this paper, we propose SPNN - a Scalable and Privacy-preserving deep Neural Network learning framework, from algorithmic-cryptographic co-perspective.

Privacy Preserving

Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification

no code implementations25 May 2020 Chaochao Chen, Jun Zhou, Longfei Zheng, Huiwen Wu, Lingjuan Lyu, Jia Wu, Bingzhe Wu, Ziqi Liu, Li Wang, Xiaolin Zheng

Recently, Graph Neural Network (GNN) has achieved remarkable progresses in various real-world tasks on graph data, consisting of node features and the adjacent information between different nodes.

Classification General Classification +2

Practical Privacy Preserving POI Recommendation

no code implementations5 Mar 2020 Chaochao Chen, Jun Zhou, Bingzhe Wu, Wenjin Fang, Li Wang, Yuan Qi, Xiaolin Zheng

Meanwhile, the public data need to be accessed by all the users are kept by the recommender to reduce the storage costs of users' devices.

Federated Learning Privacy Preserving

Adaptive Portfolio by Solving Multi-armed Bandit via Thompson Sampling

no code implementations13 Nov 2019 Mengying Zhu, Xiaolin Zheng, Yan Wang, Yuyuan Li, Qianqiao Liang

Also, by constructing multiple strategic arms, we can obtain the optimal investment portfolio to adapt different investment periods.

Decision Making Management +1

Purchase as Reward : Session-based Recommendation by Imagination Reconstruction

no code implementations ICLR 2019 Qibing Li, Xiaolin Zheng

Inspired by the prediction error minimization (PEM) and embodied cognition, we propose a simple architecture to augment reward, namely Imagination Reconstruction Network (IRN).

Session-Based Recommendations

Modeling Dynamic Missingness of Implicit Feedback for Recommendation

no code implementations NeurIPS 2018 Menghan Wang, Mingming Gong, Xiaolin Zheng, Kun Zhang

Recent studies modeled \emph{exposure}, a latent missingness variable which indicates whether an item is missing to a user, to give each missing entry a confidence of being negative feedback.

Collaborative Filtering Recommendation Systems

FinBrain: When Finance Meets AI 2.0

no code implementations26 Aug 2018 Xiaolin Zheng, Mengying Zhu, Qibing Li, Chaochao Chen, Yanchao Tan

Artificial intelligence (AI) is the core technology of technological revolution and industrial transformation.

Decision Making Management

Neural Collaborative Autoencoder

no code implementations25 Dec 2017 Qibing Li, Xiaolin Zheng, Xinyue Wu

Second, due to the difficulty on training deep neural networks, existing explicit models do not fully exploit the expressive potential of deep learning.

Collaborative Filtering Data Augmentation

Collaborative Filtering with Social Exposure: A Modular Approach to Social Recommendation

no code implementations30 Nov 2017 Menghan Wang, Xiaolin Zheng, Yang Yang, Kun Zhang

We assume that people get information of products from their online friends and they do not have to share similar preferences, which is less restrictive and seems closer to reality.

Collaborative Filtering Recommendation Systems

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