Search Results for author: Xiaokui Xiao

Found 42 papers, 16 papers with code

Predicting Cascading Failures with a Hyperparametric Diffusion Model

no code implementations12 Jun 2024 Bin Xiang, Bogdan Cautis, Xiaokui Xiao, Olga Mula, Dusit Niyato, Laks V. S. Lakshmanan

In this paper, we study cascading failures in power grids through the lens of information diffusion models.

Proof of Quality: A Costless Paradigm for Trustless Generative AI Model Inference on Blockchains

no code implementations28 May 2024 Zhenjie Zhang, Yuyang Rao, Hao Xiao, Xiaokui Xiao, Yin Yang

Unlike traditional approaches based on validating inference procedures, such as ZKML or OPML, our PoQ paradigm focuses on the outcome quality of model inference.

NeurDB: An AI-powered Autonomous Data System

no code implementations7 May 2024 Beng Chin Ooi, Shaofeng Cai, Gang Chen, Kian Lee Tan, Yuncheng Wu, Xiaokui Xiao, Naili Xing, Cong Yue, Lingze Zeng, Meihui Zhang, Zhanhao Zhao

In the wake of rapid advancements in artificial intelligence (AI), we stand on the brink of a transformative leap in data systems.

Optimizing Polynomial Graph Filters: A Novel Adaptive Krylov Subspace Approach

1 code implementation12 Mar 2024 Keke Huang, Wencai Cao, Hoang Ta, Xiaokui Xiao, Pietro Liò

To bypass eigendecomposition, polynomial graph filters are proposed to approximate graph filters by leveraging various polynomial bases for filter training.

Scalable Continuous-time Diffusion Framework for Network Inference and Influence Estimation

1 code implementation5 Mar 2024 Keke Huang, Ruize Gao, Bogdan Cautis, Xiaokui Xiao

Furthermore, we undertake an analysis of the approximation error of FIM for network inference.

Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective

no code implementations28 Feb 2024 Xinjian Luo, Yangfan Jiang, Fei Wei, Yuncheng Wu, Xiaokui Xiao, Beng Chin Ooi

We demonstrate that the sharer can execute fairness poisoning attacks to undermine the receiver's downstream models by manipulating the training data distribution of the diffusion model.

Fairness

Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs

no code implementations26 Nov 2023 Yizheng Zhu, Yuncheng Wu, Zhaojing Luo, Beng Chin Ooi, Xiaokui Xiao

In this paper, we propose a novel and highly efficient solution RiseFL for secure and verifiable data collaboration, ensuring input privacy and integrity simultaneously. Firstly, we devise a probabilistic integrity check method that significantly reduces the cost of ZKP generation and verification.

Federated Learning

Optimal Batched Best Arm Identification

no code implementations21 Oct 2023 Tianyuan Jin, Yu Yang, Jing Tang, Xiaokui Xiao, Pan Xu

Based on Tri-BBAI, we further propose the almost optimal batched best arm identification (Opt-BBAI) algorithm, which is the first algorithm that achieves the near-optimal sample and batch complexity in the non-asymptotic setting (i. e., $\delta>0$ is arbitrarily fixed), while enjoying the same batch and sample complexity as Tri-BBAI when $\delta$ tends to zero.

Passive Inference Attacks on Split Learning via Adversarial Regularization

no code implementations16 Oct 2023 Xiaochen Zhu, Xinjian Luo, Yuncheng Wu, Yangfan Jiang, Xiaokui Xiao, Beng Chin Ooi

SDAR leverages auxiliary data and adversarial regularization to learn a decodable simulator of the client's private model, which can effectively infer the client's private features under the vanilla SL, and both features and labels under the U-shaped SL.

Federated Learning

Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation

1 code implementation6 Sep 2023 Xiaochen Zhu, Vincent Y. F. Tan, Xiaokui Xiao

Graph neural networks (GNNs) have gained an increasing amount of popularity due to their superior capability in learning node embeddings for various graph inference tasks, but training them can raise privacy concerns.

Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph

1 code implementation20 Nov 2022 Haonan Wang, Jieyu Zhang, Qi Zhu, Wei Huang, Kenji Kawaguchi, Xiaokui Xiao

To answer this question, we theoretically study the concentration property of features obtained by neighborhood aggregation on homophilic and heterophilic graphs, introduce the single-pass augmentation-free graph contrastive learning loss based on the property, and provide performance guarantees for the minimizer of the loss on downstream tasks.

Contrastive Learning

DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling

1 code implementation18 Oct 2022 Jianxin Wei, Ergute Bao, Xiaokui Xiao, Yin Yang

A classic mechanism for this purpose is DP-SGD, which is a differentially private version of the stochastic gradient descent (SGD) optimizer commonly used for DNN training.

Feature Engineering Privacy Preserving

MGNNI: Multiscale Graph Neural Networks with Implicit Layers

1 code implementation15 Oct 2022 Juncheng Liu, Bryan Hooi, Kenji Kawaguchi, Xiaokui Xiao

Recently, implicit graph neural networks (GNNs) have been proposed to capture long-range dependencies in underlying graphs.

Graph Classification Graph Neural Network +1

Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits

no code implementations7 Jun 2022 Tianyuan Jin, Pan Xu, Xiaokui Xiao, Anima Anandkumar

We study the regret of Thompson sampling (TS) algorithms for exponential family bandits, where the reward distribution is from a one-dimensional exponential family, which covers many common reward distributions including Bernoulli, Gaussian, Gamma, Exponential, etc.

Multi-Armed Bandits Thompson Sampling

Differentially Private Multivariate Time Series Forecasting of Aggregated Human Mobility With Deep Learning: Input or Gradient Perturbation?

1 code implementation1 May 2022 Héber H. Arcolezi, Jean-François Couchot, Denis Renaud, Bechara Al Bouna, Xiaokui Xiao

As shown in the results, differentially private deep learning models trained under gradient or input perturbation achieve nearly the same performance as non-private deep learning models, with loss in performance varying between $0. 57\%$ to $2. 8\%$.

Decision Making Multivariate Time Series Forecasting +1

EIGNN: Efficient Infinite-Depth Graph Neural Networks

1 code implementation NeurIPS 2021 Juncheng Liu, Kenji Kawaguchi, Bryan Hooi, Yiwei Wang, Xiaokui Xiao

Motivated by this limitation, we propose a GNN model with infinite depth, which we call Efficient Infinite-Depth Graph Neural Networks (EIGNN), to efficiently capture very long-range dependencies.

Distributed Skellam Mechanism: a Novel Approach to Federated Learning with Differential Privacy

no code implementations29 Sep 2021 Ergute Bao, Yizheng Zhu, Xiaokui Xiao, Yin Yang, Beng Chin Ooi, Benjamin Hong Meng Tan, Khin Mi Mi Aung

We point out a major challenge in this problem setting: that common mechanisms for enforcing DP in deep learning, which require injecting \textit{real-valued noise}, are fundamentally incompatible with MPC, which exchanges \textit{finite-field integers} among the participants.

Federated Learning Math +1

A Fusion-Denoising Attack on InstaHide with Data Augmentation

1 code implementation17 May 2021 Xinjian Luo, Xiaokui Xiao, Yuncheng Wu, Juncheng Liu, Beng Chin Ooi

InstaHide is a state-of-the-art mechanism for protecting private training images, by mixing multiple private images and modifying them such that their visual features are indistinguishable to the naked eye.

Data Augmentation Denoising

Exploiting Explanations for Model Inversion Attacks

no code implementations ICCV 2021 Xuejun Zhao, Wencan Zhang, Xiaokui Xiao, Brian Y. Lim

We study this risk for image-based model inversion attacks and identified several attack architectures with increasing performance to reconstruct private image data from model explanations.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)

Effective and Scalable Clustering on Massive Attributed Graphs

no code implementations7 Feb 2021 Renchi Yang, Jieming Shi, Yin Yang, Keke Huang, Shiqi Zhang, Xiaokui Xiao

Given a graph G where each node is associated with a set of attributes, and a parameter k specifying the number of output clusters, k-attributed graph clustering (k-AGC) groups nodes in G into k disjoint clusters, such that nodes within the same cluster share similar topological and attribute characteristics, while those in different clusters are dissimilar.

Attribute Clustering +1

LSCALE: Latent Space Clustering-Based Active Learning for Node Classification

1 code implementation13 Dec 2020 Juncheng Liu, Yiwei Wang, Bryan Hooi, Renchi Yang, Xiaokui Xiao

We argue that the representation power in unlabelled nodes can be useful for active learning and for further improving performance of active learning for node classification.

Active Learning Clustering +2

Feature Inference Attack on Model Predictions in Vertical Federated Learning

1 code implementation20 Oct 2020 Xinjian Luo, Yuncheng Wu, Xiaokui Xiao, Beng Chin Ooi

Federated learning (FL) is an emerging paradigm for facilitating multiple organizations' data collaboration without revealing their private data to each other.

Inference Attack Vertical Federated Learning

Privacy Preserving Vertical Federated Learning for Tree-based Models

no code implementations14 Aug 2020 Yuncheng Wu, Shaofeng Cai, Xiaokui Xiao, Gang Chen, Beng Chin Ooi

Federated learning (FL) is an emerging paradigm that enables multiple organizations to jointly train a model without revealing their private data to each other.

Privacy Preserving Vertical Federated Learning

Efficient Approximation Algorithms for Adaptive Influence Maximization

2 code implementations14 Apr 2020 Keke Huang, Jing Tang, Kai Han, Xiaokui Xiao, Wei Chen, Aixin Sun, Xueyan Tang, Andrew Lim

In this paper, we propose the first practical algorithm for the adaptive IM problem that could provide the worst-case approximation guarantee of $1-\mathrm{e}^{\rho_b(\varepsilon-1)}$, where $\rho_b=1-(1-1/b)^b$ and $\varepsilon \in (0, 1)$ is a user-specified parameter.

Social and Information Networks

Analysis of Indexing Structures for Immutable Data

2 code implementations4 Mar 2020 Cong Yue, Zhongle Xie, Meihui Zhang, Gang Chen, Beng Chin Ooi, Sheng Wang, Xiaokui Xiao

We establish the worst-case guarantees of each index in terms of these five metrics, and we experimentally evaluate all indexes in a large variety of settings.

Databases

MOTS: Minimax Optimal Thompson Sampling

no code implementations3 Mar 2020 Tianyuan Jin, Pan Xu, Jieming Shi, Xiaokui Xiao, Quanquan Gu

Thompson sampling is one of the most widely used algorithms for many online decision problems, due to its simplicity in implementation and superior empirical performance over other state-of-the-art methods.

Thompson Sampling

Double Explore-then-Commit: Asymptotic Optimality and Beyond

no code implementations21 Feb 2020 Tianyuan Jin, Pan Xu, Xiaokui Xiao, Quanquan Gu

In this paper, we show that a variant of ETC algorithm can actually achieve the asymptotic optimality for multi-armed bandit problems as UCB-type algorithms do and extend it to the batched bandit setting.

Realtime Index-Free Single Source SimRank Processing on Web-Scale Graphs

no code implementations19 Feb 2020 Jieming Shi, Tianyuan Jin, Renchi Yang, Xiaokui Xiao, Yin Yang

Given a graph G and a node u in G, a single source SimRank query evaluates the similarity between u and every node v in G. Existing approaches to single source SimRank computation incur either long query response time, or expensive pre-computation, which needs to be performed again whenever the graph G changes.

Efficient Pure Exploration in Adaptive Round model

1 code implementation NeurIPS 2019 Tianyuan Jin, Jieming Shi, Xiaokui Xiao, Enhong Chen

For PAC problem, we achieve optimal query complexity and use only $O(\log_{\frac{k}{\delta}}^*(n))$ rounds, which matches the lower bound of round complexity, while most of existing works need $\Theta(\log \frac{n}{k})$ rounds.

The Disruptions of 5G on Data-driven Technologies and Applications

no code implementations6 Sep 2019 Dumitrel Loghin, Shaofeng Cai, Gang Chen, Tien Tuan Anh Dinh, Feiyi Fan, Qian Lin, Janice Ng, Beng Chin Ooi, Xutao Sun, Quang-Trung Ta, Wei Wang, Xiaokui Xiao, Yang Yang, Meihui Zhang, Zhonghua Zhang

With 5G on the verge of being adopted as the next mobile network, there is a need to analyze its impact on the landscape of computing and data management.

Networking and Internet Architecture Databases Distributed, Parallel, and Cluster Computing

Collecting and Analyzing Multidimensional Data with Local Differential Privacy

no code implementations28 Jun 2019 Ning Wang, Xiaokui Xiao, Yin Yang, Jun Zhao, Siu Cheung Hui, Hyejin Shin, Junbum Shin, Ge Yu

Motivated by this, we first propose novel LDP mechanisms for collecting a numeric attribute, whose accuracy is at least no worse (and usually better) than existing solutions in terms of worst-case noise variance.

Attribute

Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank

no code implementations17 Jun 2019 Renchi Yang, Jieming Shi, Xiaokui Xiao, Yin Yang, Sourav S. Bhowmick

Given an input graph G and a node v in G, homogeneous network embedding (HNE) maps the graph structure in the vicinity of v to a compact, fixed-dimensional feature vector.

Graph Reconstruction Link Prediction +2

Privacy-preserving Stochastic Gradual Learning

no code implementations30 Sep 2018 Bo Han, Ivor W. Tsang, Xiaokui Xiao, Ling Chen, Sai-fu Fung, Celina P. Yu

PRESTIGE bridges private updates of the primal variable (by private sampling) with the gradual curriculum learning (CL).

Privacy Preserving Stochastic Optimization

Refutations on "Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study"

2 code implementations15 May 2017 Wei Lu, Xiaokui Xiao, Amit Goyal, Keke Huang, Laks V. S. Lakshmanan

In a recent SIGMOD paper titled "Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study", Arora et al. [1] undertake a performance benchmarking study of several well-known algorithms for influence maximization.

Social and Information Networks

Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms

no code implementations AAAI 2017 Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier, Xiaokui Xiao

To achieve this task, one effective approach is to exploit relations between aspect terms and opinion terms by parsing syntactic structure for each sentence.

Extract Aspect Sentence

Collecting and Analyzing Data from Smart Device Users with Local Differential Privacy

no code implementations16 Jun 2016 Thông T. Nguyên, Xiaokui Xiao, Yin Yang, Siu Cheung Hui, Hyejin Shin, Junbum Shin

Organizations with a large user base, such as Samsung and Google, can potentially benefit from collecting and mining users' data.

Databases

PrivBayes: Private Data release via Bayesian networks

no code implementations Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data 2014 Jun Zhang, Graham Cormode, Cecilia M. Procopiuc, Divesh Srivastava, Xiaokui Xiao

Given a dataset D, PRIVBAYES first constructs a Bayesian network N , which (i) provides a succinct model of the correlations among the attributes in D and (ii) allows us to approximate the distribution of data in D using a set P of lowdimensional marginals of D. After that, PRIVBAYES injects noise into each marginal in P to ensure differential privacy, and then uses the noisy marginals and the Bayesian network to construct an approximation of the data distribution in D. Finally, PRIVBAYES samples tuples from the approximate distribution to construct a synthetic dataset, and then releases the synthetic data.

Privacy Preserving

Influence Maximization: Near-Optimal Time Complexity Meets Practical Efficiency

3 code implementations3 Apr 2014 Youze Tang, Xiaokui Xiao, Yanchen Shi

Given a social network G and a constant k, the influence maximization problem asks for k nodes in G that (directly and indirectly) influence the largest number of nodes under a pre-defined diffusion model.

Social and Information Networks Databases

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