GRAND ensures node-level differential privacy for network data.
problem Lack of node-level differential privacy for network data.
method Proposes GRAND, the first mechanism for releasing networks with node-level differential privacy and preserving structural properties.
result GRAND releases networks while ensuring node-level differential privacy and preserving structural properties.
New method for online learning IC models with node-level feedback.
problem Learning IC models with node-level feedback in social networks.
method Detailed analysis and online algorithm with O ( T ) \mathcal{O}( \sqrt{T}) O ( T ) cumulative regret. result First confidence-region result and online algorithm for IC models with node-level feedback.
New methods test correlation between network structure and node features.
problem Assessing correlation between network structure and node-level covariates.
method Four novel methods based on linear models and canonical correlation analysis.
result Theoretical guarantees and computational efficiency for testing network dependency.
Graph transformers outperform graph convolutions by preserving community information.
problem Understanding why graph transformers perform well in node-level prediction tasks.
method Analyzing the Gaussian process limits of graph transformers with infinite width and infinite heads.
result Graph transformers maintain discriminative node representations even in deep layers, preventing oversmoothing.
CopulaGNN integrates graph representational and correlational roles for better node-level predictions.
problem Graphs encode diverse roles in node-level prediction tasks, but GNNs struggle with correlational information.
method Copula theory to describe multivariate dependence, integrating representational and correlational graph information.
result CopulaGNN improves GNN performance on regression tasks by leveraging both types of graph information.
Graph neural networks improve predictions on graph data.
problem Complex non-Euclidean graph data limits traditional machine learning methods.
method Graph neural networks for node-level predictions.
result Improved handling of large-scale and time-dynamic graphs.
This work evaluates graph models' robustness to structural distributional shifts.
problem Evaluating graph models' robustness to structural distributional shifts.
method Proposes a general approach for inducing diverse distributional shifts based on graph structure.
result Simple models often outperform more sophisticated methods on structural distributional shifts.
Understanding how users navigate in a network is of high interest in many applications. We consider a setting where only aggregate node-level traffic is observed and tackle the task of learning edge transition probabilities. We cast it as a preference learning problem, and we study a model where choices follow Luce's a…
In this paper we consider the task of detecting abnormal communication volume occurring at node-level in communication networks. The signal of the communication activity is modeled by means of a clique stream: each occurring communication event is instantaneous and activates an undirected subgraph spanning over a set o…
NGAT predicts long-term stock trends using graph attention networks.
problem Lack of effective corporate relationship graph comparison methods and model complexity in stock prediction.
method Developed a Node-level Graph Attention Network (NGAT) for corporate relationship graphs.
result Demonstrated the effectiveness of NGAT across two datasets.
Predicating macroscopic influences of drugs on human body, like efficacy and toxicity, is a central problem of small-molecule based drug discovery. Molecules can be represented as an undirected graph, and we can utilize graph convolution networks to predication molecular properties. However, graph convolutional network…
iGCL preserves graph semantics in latent space augmentations.
problem Manual tuning of augmentation ratios and unexpected graph changes.
method iGCL uses a Variational Graph Auto-Encoder to learn augmentations in the latent space, optimizing an upper bound for contrastive loss.
result iGCL achieves state-of-the-art performance on graph-level and node-level tasks.
Proposes a novel graph representation learning framework using contrastive methods.
problem Graph representation learning for graph-structured data.
method Leverages a contrastive objective at the node level, generating two graph views by corruption and learning node representations by maximizing agreement.
result Consistently outperforms existing state-of-the-art methods on transductive and inductive learning tasks.
BART and MOTR-BART improve tree-based predictions with local linear models.
problem Non-linearity and high-order interactions in data.
method Bayesian Additive Regression Trees (BART) and Model Trees BART (MOTR-BART) using piecewise linear functions.
result MOTR-BART achieves equal or better performance with fewer trees than BART.
Proposes a new method to describe graph vertex features using characteristic functions.
problem Describing the distribution of vertex features at multiple scales on graphs.
method Introduces FEATHER, a computationally efficient algorithm to calculate characteristic functions based on random walk transition probabilities.
result Demonstrates that the proposed method creates high-quality graph representations and is robust to data corruption.
Generative model for inferring graph from time series data.
problem Generating graphs conditioned on multivariate time series data.
method Time Series Conditioned Graph Generation-Generative Adversarial Networks (TSGG-GAN).
result Demonstrates effectiveness and generalizability of TSGG-GAN on synthetic and real-world datasets.
New framework models epistemic uncertainty in GNNs using random sets.
problem Uncertainty in graph neural network predictions.
method Introduces a belief function (random set) approach to model epistemic uncertainty in GNNs.
result Demonstrates superior uncertainty quantification on various graph datasets.
This paper proposes a method to learn graph representations by partitioning edges into communities.
problem Graph neural networks ignore how edges are formed, leading to suboptimal representation learning.
method Introduces a generative model to partition edges into community-specific weighted edges, then uses these for GNN-based inference and classification.
result The method learns discriminative representations for both node-level and graph-level classification tasks.
This paper improves GNN robustness by aligning feature and adjacency matrix learning.
problem Improving robustness of graph neural networks (GNN) in noisy graph data.
method Proposes a novel regularized GSL approach that aligns feature information and graph information, incorporating sparse dimensional reduction.
result Demonstrates superior performance in noisy graph structures compared to competitive baselines.
SubGNN tackles subgraph prediction challenges in graphs.
problem Subgraphs in graphs are challenging to predict due to their internal topology and external connectivity.
method SubGNN introduces a novel subgraph routing mechanism to learn disentangled subgraph representations.
result SubGNN achieves considerable performance gains on subgraph classification tasks, outperforming strong baseline methods.
DECAF-GAD improves fairness in autoencoder-based GAD models without sacrificing performance.
problem Fairness in autoencoder-based GAD models for node-level anomaly detection.
method DECAF-GAD uses a structural causal model to disentangle sensitive attributes from learned representations, along with a fairness-guided loss function.
result DECAF-GAD significantly enhances fairness metrics while maintaining anomaly detection performance.
Improves privacy amplification by shuffling for differential privacy.
problem Enhancing privacy guarantees in systems with anonymous data contributions.
method Theoretical and numerical analysis of Rényi differential privacy parameters and privacy amplification by shuffling.
result First asymptotically optimal analysis of Rényi differential privacy parameters for shuffled outputs.
Proposes a privacy-preserving recommendation system using matrix factorization and differential privacy.
problem Privacy leakage in recommendation systems when anonymizing user data is not sufficient.
method Uses matrix factorization and differential privacy via the Gaussian mechanism.
result Demonstrates excellent utility for privacy-preserving recommendation systems.
PSimGNN partitions graphs into subgraphs for efficient graph similarity computation.
problem Efficiently compute graph similarity scores for large graphs.
method Graph partitioning followed by subgraph-level and node-level comparisons using a graph neural network.
result PSimGNN outperforms state-of-the-art methods in graph similarity computation tasks.
This work optimizes mean estimation under varying privacy constraints.
problem Mean estimation with heterogeneous privacy constraints.
method Proposes an algorithm for mean estimation under different privacy levels for users.
result Shows a saturation phenomenon in performance as privacy levels are relaxed.
Improves privacy guarantees by analyzing randomness in privacy-preserving mechanisms.
problem Balancing user privacy and business constraints in privacy-preserving mechanisms.
method Analyzes explicit and implicit randomness in privacy mechanisms and proposes a probabilistic calibration method.
result Proposes privacy at risk, providing stronger privacy guarantees with quantifiable risks.
The paper analyzes and proposes methods for privately sharing individual privacy losses using per-instance differential privacy.
problem The standard differential privacy framework provides a worst-case bound that may not accurately reflect individual privacy losses.
method The paper analyzes per-instance differential privacy and proposes methods to privately and accurately publish per-instance privacy losses.
result The methods privately and accurately publish per-instance differential privacy losses with minimal additional privacy cost.
This work optimizes mean estimation under varying user privacy demands.
problem Mean estimation with heterogeneous privacy levels.
method Proposes an algorithm that is minimax optimal and has near-linear run-time.
result Privacy requirements of the most stringent users dictate overall error rates.
A new privacy accountant for Gaussian differential privacy measures individual privacy losses.
problem Bounding differential privacy loss for each participant in data analysis.
method Developed a privacy accountant for adaptive compositions of randomised mechanisms using Gaussian differential privacy.
result Provided optimal bounds for the Gaussian mechanism and constructed an approximative individual privacy accountant.
Paper simplifies DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.
problem Tension between efficiency and flexibility in DP composition theorems.
method Rényi Differential Privacy (RDP) for adaptive privacy budgets, proving simpler composition theorem with smaller constants.
result Practical DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.
This paper bounds min-entropy leakage for Blowfish privacy using graph symmetries.
problem Bounding min-entropy leakage for Blowfish privacy mechanisms.
method Organizing analysis over symmetrical partitions corresponding to orbits of graph automorphism groups.
result Demonstrates a construction meeting the bound with asymptotic equality, showing tightness.
New federated f f f -differential privacy for collaborative learning.
problem Privacy in federated learning.
method Introducing federated f f f -differential privacy and proposing a generic private federated learning framework. result Proves federated f f f -differential privacy provides privacy guarantee on each record of one client's data. Differential privacy is a statistical concept that can be explained through hypothesis testing.
problem Formalizing differential privacy as a statistical concept.
method Using David Blackwell's informativeness theorem, the paper shows differential privacy can be understood through hypothesis testing.
result The definition of f f f -differential privacy provides a unified framework for analyzing privacy bounds. A new method for tighter privacy loss accounting in adaptive analyses.
problem Ensuring individual privacy in adaptive analyses while staying within a privacy budget.
method A personalized privacy loss estimate and a Rényi differential privacy filter.
result Personalized privacy loss accounting can be practical and tighter than existing methods.
Paper tackles federated learning with privacy, enhancing target data analysis.
problem Heterogeneity and privacy of distributed data in federated learning.
method Formulates federated differential privacy, studies statistical problems under privacy constraints.
result Federated differential privacy offers a balance between privacy and knowledge transfer.
Unified framework for subsampling mechanisms with tighter privacy guarantees.
problem Improving privacy in machine learning models through subsampling.
method Conditional optimal transport for deriving mechanism-specific subsampling guarantees.
result Tighter privacy bounds for subsampled mechanisms compared to traditional methods.
New findings show privacy affects generalization error in a non-monotonic way.
problem Privacy and robustness in distributed learning.
method Theoretical analysis and matching lower/upper bounds on algorithmic stability.
result Generalization error is non-monotonically affected by privacy, depending on noise level.
New privacy framework tailored to specific data distributions.
problem Protecting individual data points in decision-making processes.
method Introducing tangent differential privacy, a new form of differential privacy.
result Entropic regularization guarantees tangent differential privacy under general conditions.
Addresses theoretical and practical aspects of Gaussian differential privacy.
problem Theoretical and practical challenges in privacy-preserving data analysis.
method Discussion of f-differential privacy and Gaussian differential privacy.
result Gaussian differential privacy can enhance privacy in various applications.
New filters match advanced composition for adaptive privacy, with practical constants.
problem Limitations of existing adaptive composition methods.
method Constructed new filters and odometers that match advanced composition rates, including constants.
result Achieved fully adaptive privacy with practical filters and odometers.
Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train neural networks subject to privacy constraints that are specified by differential…
Missing data enhances privacy in differential privacy.
problem Privacy preservation in datasets with missing values.
method Formalized missing data as a privacy amplification mechanism within differential privacy.
result Incomplete data can yield privacy amplification for differentially private algorithms.
We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy loss bounds. We adapt the Bayesian privacy accounting method to the federated sett…
This paper proposes a new differential privacy definition using Rao distance.
problem Improving differential privacy definitions for better sequential composition.
method Using Rao distance instead of divergences of densities to define privacy.
result Proposed definition shares interpretation with previous definitions but improves sequential composition.
BCDP enhances privacy by protecting sensitive features more precisely.
problem Uniform privacy protection in LDP degrades performance for sensitive features.
method Bayesian Coordinate Differential Privacy (BCDP) adjusts privacy protection per feature sensitivity.
result BCDP improves accuracy in downstream tasks without sacrificing privacy.
Edgeworth Accountant calculates privacy loss under differential privacy compositions efficiently.
problem Efficiently computing overall privacy loss under composition of private algorithms.
method Analytical approach using f f f -differential privacy framework and Edgeworth expansion. result Non-asymptotic ( ε , δ ) (ε, δ) ( ε , δ ) -differential privacy bounds with reduced computational cost. Improved privacy bounds enhance deep learning training efficiency.
problem Enhancing privacy guarantees in deep learning models.
method Deriving optimal DP parameters using f f f -divergences. result Significantly reduces the number of iterations needed for training deep learning models.
Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, ε ε ε , about how much information is leaked by a mechanism. However, implementations of privacy-preserving machine learning often select large values of ε ε ε in order to get acceptable utility of …