Contrastive explainable clustering with differential privacy
- URL: http://arxiv.org/abs/2406.04610v1
- Date: Fri, 7 Jun 2024 03:37:36 GMT
- Title: Contrastive explainable clustering with differential privacy
- Authors: Dung Nguyen, Ariel Vetzler, Sarit Kraus, Anil Vullikanti,
- Abstract summary: This paper presents a novel approach in Explainable AI (XAI) integrating contrastive explanations with differential privacy in clustering methods.
For several basic clustering problems, including $k$-median and $k$-means, we give efficient differential private contrastive explanations.
In each contrastive scenario, we designate a specific data point as the fixed centroid position, enabling us to measure the impact of this constraint on clustering utility under differential privacy.
- Score: 25.19112971690494
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: This paper presents a novel approach in Explainable AI (XAI), integrating contrastive explanations with differential privacy in clustering methods. For several basic clustering problems, including $k$-median and $k$-means, we give efficient differential private contrastive explanations that achieve essentially the same explanations as those that non-private clustering explanations can obtain. We define contrastive explanations as the utility difference between the original clustering utility and utility from clustering with a specifically fixed centroid. In each contrastive scenario, we designate a specific data point as the fixed centroid position, enabling us to measure the impact of this constraint on clustering utility under differential privacy. Extensive experiments across various datasets show our method's effectiveness in providing meaningful explanations without significantly compromising data privacy or clustering utility. This underscores our contribution to privacy-aware machine learning, demonstrating the feasibility of achieving a balance between privacy and utility in the explanation of clustering tasks.
Related papers
- Improving the Utility of Differentially Private Clustering through
Dynamical Processing [2.954235682505971]
This paper aims to alleviate the trade-off between utility and privacy in the task of differentially private clustering.
Our framework achieves better clustering performance at the same privacy level, compared to the existing methods.
arXiv Detail & Related papers (2023-04-27T00:13:17Z) - k-Means SubClustering: A Differentially Private Algorithm with Improved
Clustering Quality [0.0]
Many differentially private iterative algorithms have been proposed in interactive settings to protect an individual's privacy from inference attacks.
In this work, we extend the previous work on 'Differentially Private k-Means Clustering With Convergence Guarantee' by taking it as our baseline.
The novelty of our approach is to sub-cluster the clusters and then select the centroid which has a higher probability of moving in the direction of the future centroid.
arXiv Detail & Related papers (2023-01-07T17:07:12Z) - Inv-SENnet: Invariant Self Expression Network for clustering under
biased data [17.25929452126843]
We propose a novel framework for jointly removing unwanted attributes (biases) while learning to cluster data points in individual subspaces.
Our experimental result on synthetic and real-world datasets demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2022-11-13T01:19:06Z) - A One-shot Framework for Distributed Clustered Learning in Heterogeneous
Environments [54.172993875654015]
The paper proposes a family of communication efficient methods for distributed learning in heterogeneous environments.
One-shot approach, based on local computations at the users and a clustering based aggregation step at the server is shown to provide strong learning guarantees.
For strongly convex problems it is shown that, as long as the number of data points per user is above a threshold, the proposed approach achieves order-optimal mean-squared error rates in terms of the sample size.
arXiv Detail & Related papers (2022-09-22T09:04:10Z) - Differentially-Private Clustering of Easy Instances [67.04951703461657]
In differentially private clustering, the goal is to identify $k$ cluster centers without disclosing information on individual data points.
We provide implementable differentially private clustering algorithms that provide utility when the data is "easy"
We propose a framework that allows us to apply non-private clustering algorithms to the easy instances and privately combine the results.
arXiv Detail & Related papers (2021-12-29T08:13:56Z) - Discriminative Attribution from Counterfactuals [64.94009515033984]
We present a method for neural network interpretability by combining feature attribution with counterfactual explanations.
We show that this method can be used to quantitatively evaluate the performance of feature attribution methods in an objective manner.
arXiv Detail & Related papers (2021-09-28T00:53:34Z) - You Never Cluster Alone [150.94921340034688]
We extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation.
We define a set of categorical variables as clustering assignment confidence, which links the instance-level learning track with the cluster-level one.
By reparametrizing the assignment variables, TCC is trained end-to-end, requiring no alternating steps.
arXiv Detail & Related papers (2021-06-03T14:59:59Z) - Graph Contrastive Clustering [131.67881457114316]
We propose a novel graph contrastive learning framework, which is then applied to the clustering task and we come up with the Graph Constrastive Clustering(GCC) method.
Specifically, on the one hand, the graph Laplacian based contrastive loss is proposed to learn more discriminative and clustering-friendly features.
On the other hand, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments.
arXiv Detail & Related papers (2021-04-03T15:32:49Z) - Deep Clustering by Semantic Contrastive Learning [67.28140787010447]
We introduce a novel variant called Semantic Contrastive Learning (SCL)
It explores the characteristics of both conventional contrastive learning and deep clustering.
It can amplify the strengths of contrastive learning and deep clustering in a unified approach.
arXiv Detail & Related papers (2021-03-03T20:20:48Z) - Differentially Private k-Means Clustering with Guaranteed Convergence [5.335316436366718]
Iterative clustering algorithms help us to learn the insights behind the data.
It may allow adversaries to infer the privacy of individuals with some background knowledge.
To protect individual privacy against such an inference attack, preserving differential privacy (DP) for the iterative clustering algorithms has been extensively studied.
arXiv Detail & Related papers (2020-02-03T22:53:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.