Search

Graph-based fraud detection has widespread application in modern industry scenarios, such as spam review and malicious account detection. While considerable efforts have been devoted to designing adequate fraud detectors, the interpretability of their results has often been overlooked. Previous works have attempted to generate explanations for specific instances using post-hoc explaining methods such as a GNNExplainer. However, post-hoc explanations can not facilitate the model predictions and the computational cost of these methods cannot meet practical requirements, thus limiting their application in real-world scenarios. To address these issues, we propose SEFraud, a novel graph-based self-explainable fraud detection framework that simultaneously tackles fraud detection and result in interpretability. Concretely, SEFraud first leverages customized heterogeneous graph transformer networks with learnable feature masks and edge masks to learn expressive representations from the informative heterogeneously typed transactions. A new triplet loss is further designed to enhance the performance of mask learning. Empirical results on various datasets demonstrate the effectiveness of SEFraud as it shows considerable advantages in both the fraud detection performance and interpretability of prediction results. Moreover, SEFraud has been deployed and offers explainable fraud detection service for the largest bank in China, Industrial and Commercial Bank of China Limited (ICBC). Results collected from the production environment of ICBC show that SEFraud can provide accurate detection results and comprehensive explanations that align with the expert business understanding, confirming its efficiency and applicability in large-scale online services., Comment: Accepted by KDD 2024

Metalenses can achieve diffraction-limited focusing through localized phase manipulation of the incoming light beam. Because these structures are ultrathin, less than a wavelength, this has the potential of achieving ultrathin optical elements, with a thickness limited mainly by the mechanical strength of the transparent substrate. Recently proposed metalenses are based on either dielectric nanofin arrays, or nanoparticles of large number, which leads to severe manufacturing challenges. To overcome these challenges, this paper predicts a new type of metalens with concentric-nanoring topology, where the number and size of the nanorings are determined using an inverse design method. By focusing the electrical field energy at a specified position, the convex-like metalens is inversely predicted with desired numerical aperture and a diffraction-limited focal spot. The Poynting vector distribution found demonstrates the mechanism of the lensing function, in which optical vortices are generated in the nanorings to achieve a matching of the phase and impedance between the substrate and free space, and further, to form a spherical wavefront and enhance the transmission of the optical energy. The inverse design method can also be extended to predict an axicon-like metalens with focal beam. The improved manufacturability is concluded from the geometry of the concentric-nanoring configurations.

This paper has presented inversely determining the resonant configuration of the bilateral nanostructures for periodic metallic slits with extraordinary optical transmission performance. The topology optimization approach is utilized to implement the inverse design procedure. Several geometrical configurations of the bilateral nanostructures are derived for periodic metallic slits. The resonant performance of the derived nanostructures are demonstrated by the transmission spectra, where the transmission peak is presented at the specified wavelength in the inverse design procedure. This provides an approach to control the red or blue shift of the transmission peak or localize the resonant performance at a desired frequency, by specifying the desired incident wavelength in the inverse design procedure. The inverse design method is extended to make the periodic metallic slits to be less sensitive to the incident wavelength. This research can be further extended to inversely find the resonant subwavelength structures for extraordinary optical absorption and other surface palsmon polariton based photonic devices. The inverse design of three dimensional apertures for extraordinary optical transmission will be investigated in our future researches.

This paper presents an optimal control-based inverse method used to determine the distribution of the electrodes for the electroosmotic micromixers with external driven flow from the inlet. Based on the optimal control method, one Dirichlet boundary control problem is constructed to inversely find the optimal distribution of the electrodes on the sidewalls of electroosmotic micromixers and achieve the acceptable mixing performance. After solving the boundary control problem, the step-shaped distribution of the external electric potential imposed on the sidewalls can be obtained and the distribution of electrodes can be inversely determined according to the obtained external electric potential. Numerical results are also provided to demonstrate the effectivity of the proposed method.