Search Results for author:
Found 32 papers, 12 papers with code
Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy
Deep neural networks have strong capabilities of memorizing the underlying training data, which can be a serious privacy concern.
Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph
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 graph contrastive learning loss based on the property, and provide performance guarantees for the minimizer of the loss on downstream tasks.
DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
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.
MGNNI: Multiscale Graph Neural Networks with Implicit Layers
Recently, implicit graph neural networks (GNNs) have been proposed to capture long-range dependencies in underlying graphs.
The Metaverse Data Deluge: What Can We Do About It?
In the Metaverse, the physical space and the virtual space co-exist, and interact simultaneously.
Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits
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.
Dangling-Aware Entity Alignment with Mixed High-Order Proximities
We study dangling-aware entity alignment in knowledge graphs (KGs), which is an underexplored but important problem.
Differentially Private Multivariate Time Series Forecasting of Aggregated Human Mobility With Deep Learning: Input or Gradient Perturbation?
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 $2. 8\%$.
EIGNN: Efficient Infinite-Depth Graph Neural Networks
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
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.
A Fusion-Denoising Attack on InstaHide with Data Augmentation
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.
Exploiting Explanations for Model Inversion Attacks
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.
Effective and Scalable Clustering on Massive Attributed Graphs
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.
LSCALE: Latent Space Clustering-Based Active Learning for Node Classification
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.
Feature Inference Attack on Model Predictions in Vertical Federated Learning
Federated learning (FL) is an emerging paradigm for facilitating multiple organizations' data collaboration without revealing their private data to each other.
Privacy Preserving Vertical Federated Learning for Tree-based Models
Federated learning (FL) is an emerging paradigm that enables multiple organizations to jointly train a model without revealing their private data to each other.
Efficient Approximation Algorithms for Adaptive Influence Maximization
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
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
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.
Double Explore-then-Commit: Asymptotic Optimality and Beyond
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
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
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
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
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.
Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank
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.
Privacy-preserving Stochastic Gradual Learning
PRESTIGE bridges private updates of the primal variable (by private sampling) with the gradual curriculum learning (CL).
Refutations on "Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study"
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
To achieve this task, one effective approach is to exploit relations between aspect terms and opinion terms by parsing syntactic structure for each sentence.
Collecting and Analyzing Data from Smart Device Users with Local Differential Privacy
Organizations with a large user base, such as Samsung and Google, can potentially benefit from collecting and mining users' data.
Databases
Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis
Previous studies have shown that exploiting connections between aspect and opinion terms is promising for this task.
PrivBayes： Private Data release via Bayesian networks
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.
Influence Maximization: Near-Optimal Time Complexity Meets Practical Efficiency
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
