Multi-objective Privacy-preserving Text Representation Learning

Zhan, Huixin; Zhang, Kun; Hu, Chenyi; Sheng, Victor S.

doi:10.1145/3459637.3482147

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Completed Research and Timeline Me and my Ph.D. advisor have been researching privacy-preserving text representations. In our paper (Zhan et al 2021), we show that some of the hidden private information correlates with the output labels and therefore can be learned by a neural network. In such a case, there is a tradeoff between the utility of the representation and its privacy.…”

Section: Research Planmentioning

confidence: 82%

Privacy-Preserving Representation Learning for Text-Attributed Networks with Simplicial Complexes

Zhan¹,

Sheng²

2023

AAAI

View full text Add to dashboard Cite

Although recent network representation learning (NRL) works in text-attributed networks demonstrated superior performance for various graph inference tasks, learning network representations could always raise privacy concerns when nodes represent people or human-related variables. Moreover, standard NRLs that leverage structural information from a graph proceed by first encoding pairwise relationships into learned representations and then analysing its properties. This approach is fundamentally misaligned with problems where the relationships involve multiple points, and topological structure must be encoded beyond pairwise interactions. Fortunately, the machinery of topological data analysis (TDA) and, in particular, simplicial neural networks (SNNs) offer a mathematically rigorous framework to evaluate not only higher-order interactions, but also global invariant features of the observed graph to systematically learn topological structures. It is critical to investigate if the representation outputs from SNNs are more vulnerable compared to regular representation outputs from graph neural networks (GNNs) via pairwise interactions. In my dissertation, I will first study learning the representations with text attributes for simplicial complexes (RT4SC) via SNNs. Then, I will conduct research on two potential attacks on the representation outputs from SNNs: (1) membership inference attack, which infers whether a certain node of a graph is inside the training data of the GNN model; and (2) graph reconstruction attacks, which infer the confidential edges of a text-attributed network. Finally, I will study a privacy-preserving deterministic differentially private alternating direction method of multiplier to learn secure representation outputs from SNNs that capture multi-scale relationships and facilitate the passage from local structure to global invariant features on text-attributed networks.

show abstract

Section: Research Planmentioning

confidence: 82%

Privacy-Preserving Representation Learning for Text-Attributed Networks with Simplicial Complexes

Zhan¹,

Sheng²

2023

AAAI

View full text Add to dashboard Cite

show abstract

“…Another line of works is related to random walks on HOGDMs as a way of harnessing HO for learning graph representations. This includes works dedicated to hypergraphs [4], [72], [81], [84], [128], [129], [168], [214], [277], hyper-networks [236], and simplicial complexes [53], [119], [270].…”

Section: Work Related To Higher-order Gnnsmentioning

confidence: 99%

Motif Prediction with Graph Neural Networks

Besta¹,

Grob²,

Miglioli³

et al. 2022

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Link prediction is one of the central problems in graph mining. However, recent studies highlight the importance of higher-order network analysis, where complex structures called motifs are the first-class citizens. We first show that existing link prediction schemes fail to effectively predict motifs. To alleviate this, we establish a general motif prediction problem and we propose several heuristics that assess the chances for a specified motif to appear. To make the scores realistic, our heuristics consider -among others -correlations between links, i.e., the potential impact of some arriving links on the appearance of other links in a given motif. Finally, for highest accuracy, we develop a graph neural network (GNN) architecture for motif prediction. Our architecture offers vertex features and sampling schemes that capture the rich structural properties of motifs. While our heuristics are fast and do not need any training, GNNs ensure highest accuracy of predicting motifs, both for dense (e.g., 𝑘-cliques) and for sparse ones (e.g., 𝑘-stars). We consistently outperform the best available competitor by more than 10% on average and up to 32% in area under the curve. Importantly, the advantages of our approach over schemes based on uncorrelated link prediction increase with the increasing motif size and complexity. We also successfully apply our architecture for predicting more arbitrary clusters and communities, illustrating its potential for graph mining beyond motif analysis. CCS CONCEPTS• Information systems → Data mining.

show abstract