No abstract

No abstract

Graph Neural Networks (GNNs) are a popular technique for modelling graphstructured data that compute node-level representations via aggregation of information from the local neighborhood of each node. However, this aggregation implies increased risk of revealing sensitive information, as a node can participate in the inference for multiple nodes. This implies that standard privacy preserving machine learning techniques, such as differentially private stochastic gradient descent (DP-SGD) -which are designed for situations where each data point participates in the inference for one point only -either do not apply, or lead to inaccurate solutions. In this work, we formally define the problem of learning 1-layer GNNs with node-level privacy, and provide an algorithmic solution with a strong differential privacy guarantee. Even though each node can be involved in the inference for multiple nodes, by employing a careful sensitivity analysis and a non-trivial extension of the privacy-by-amplification technique, our method is able to provide accurate solutions with solid privacy parameters. Empirical evaluation on standard benchmarks demonstrates that our method is indeed able to learn accurate privacy preserving GNNs, while still outperforming standard non-private methods that completely ignore graph information.

The effect of different electrolytes on the sorption of the hydrolyzed form of four different reactive dyes has been investigated. The electrolytes studied were sodium, ammonium, Jithium, and magnesium chlorides, and ammonium sulfate, which differ widely in their ability to increase the sorption of hydrolyzed reactive dyes by cellulose. Their relative efficiencies were in the order: ammonium chloride > ammonium sulfate > sodium chloride > lithium chloride ~ magnesium chloride. The effect of the electrolytes has been discussed in terms of partial screening of the surface charge on cellulose by the crowding of the cations at the cellulose-water interface, pH of the bath, and the ability to modify the structure of water. The ability of the electrolytes to modify the pH of the solution plays a dominant role in sorption increase at lower con centrations of electrolytes, whereas at higher concentrations the ability of the electrolytes to modify the cellulose-water interface plays a decisive role.

No abstract