TY  - JOUR
AB  - Graph Neural Networks (GNNs) have established themselves as state-of-the-art for many machine learning applications such as the analysis of social and medical networks. Several among these datasets contain privacy-sensitive data. Machine learning with differential privacy is a promising technique to allow deriving insight from sensitive data while offering formal guarantees of privacy protection. However, the differentially private training of GNNs has so far remained under-explored due to the challenges presented by the intrinsic structural connectivity of graphs. In this work, we introduce a framework for differential private graph-level classification. Our method is applicable to graph deep learning on multi-graph datasets and relies on differentially private stochastic gradient descent (DP-SGD). We show results on a variety of datasets and evaluate the impact of different GNN architectures and training hyperparameters on model performance for differentially private graph classification, as well as the scalability of the method on a large medical dataset. Our experiments show that DP-SGD can be applied to graph classification tasks with reasonable utility losses. Furthermore, we apply explainability techniques to assess whether similar representations are learned in the private and non-private settings. Our results can also function as robust baselines for future work in this area.
AU  - Mueller, T.T.*
AU  - Paetzold, J.C.
AU  - Prabhakar, C.*
AU  - Usynin, D.*
AU  - Rueckert, D.*
AU  - Kaissis, G.
C1  - 69412
C2  - 53860
CY  - 10662 Los Vaqueros Circle, Po Box 3014, Los Alamitos, Ca 90720-1314 Usa
SP  - 7308-7318
TI  - Differentially private graph neural networks for whole-graph classification.
JO  - IEEE Trans. Pattern Anal. Mach. Intell.
VL  - 45
IS  - 6
PB  - Ieee Computer Soc
PY  - 2023
SN  - 0162-8828
ER  - 

TY  - JOUR
AB  - Median filtering is among the most utilized tools for smoothing real-valued data, as it is robust, edge-preserving, value-preserving, and yet can be computed efficiently. For data living on the unit circle, such as phase data or orientation data, a filter with similar properties is desirable. For these data, there is no unique means to define a median; so we discuss various possibilities. The arc distance median turns out to be the only variant which leads to robust, edge-preserving and value-preserving smoothing. However, there are no efficient algorithms for filtering based on the arc distance median. Here, we propose fast algorithms for filtering of signals and images with values on the unit circle based on the arc distance median. For non-quantized data, we develop an algorithm that scales linearly with the filter size. The runtime of our reference implementation is only moderately higher than the Matlab implementation of the classical median filter for real-valued data. For quantized data, we obtain an algorithm of constant complexity w.r.t. the filter size. We demonstrate the performance of our algorithms for real life data sets: phase images from interferometric synthetic aperture radar, planar flow fields from optical flow, and time series of wind directions.
AU  - Storath, M.*
AU  - Weinmann, A.
C1  - 53031
C2  - 44282
CY  - Los Alamitos
SP  - 639-652
TI  - Fast median filtering for phase or orientation data.
JO  - IEEE Trans. Pattern Anal. Mach. Intell.
VL  - 40
IS  - 3
PB  - Ieee Computer Soc
PY  - 2018
SN  - 0162-8828
ER  - 

TY  - JOUR
AB  - This paper describes a novel method to acquire depth images using a pair of ToF (Time of Flight) cameras. As opposed to approaches that filter, calibrate or do 3D reconstructions posterior to the image acquisition, we combine the measurements of the two cameras within a modified acquisition procedure. The new proposed stereo-ToF acquisition is composed of three stages during which we actively modify the infrared lighting of the scene: first, the two cameras emit an infrared signal one after the other (stages 1 and 2), and then, simultaneously (stage 3). Assuming the scene is static during the three stages, we gather the depth measurements obtained with both cameras and define a cost function to optimize the two depth images. A qualitative and quantitative evaluation of the performance of the proposed stereo-ToF acquisition is provided both for simulated and real ToF cameras. In both cases, the stereo-ToF acquisition produces more accurate depth measurements. Moreover, an extension to the multi-view ToF case and a detailed study on the interference specifications of the system are included.
AU  - Castaneda, V.*
AU  - Mateus, D.
AU  - Navab, N.*
C1  - 28225
C2  - 33013
SP  - 1402-1413
TI  - Stereo time-of-flight with constructive interference.
JO  - IEEE Trans. Pattern Anal. Mach. Intell.
VL  - 36
IS  - 7
PB  - IEEE
PY  - 2013
SN  - 0162-8828
ER  - 

TY  - JOUR
AB  - We introduce Schroedinger Eigenmaps (SE), a new semi-supervised manifold learning and recovery technique. This method is based on an implementation of graph Schroedinger operators with appropriately constructed barrier potentials as carriers of labeled information. We use our approach for the analysis of standard biomedical datasets and new multispectral retinal images.
AU  - Czaja, W.*
AU  - Ehler, M.
C1  - 23745
C2  - 31285
SP  - 1274-1280
TI  - Schroedinger eigenmaps for the analysis of biomedical data.
JO  - IEEE Trans. Pattern Anal. Mach. Intell.
VL  - 35
IS  - 5
PB  - IEEE Computer Soc.
PY  - 2013
SN  - 0162-8828
ER  -