Graph Neural Networks (GNNs) have gained the interest of industry with Relational Graph Convolutional Networks (R-GCNs) showing promise for fraud detection. Taking existing workflows that leverage graph features to train a gradient boosted decision tree (GBDT) and replacing the graph features with GNN produced embedding achieves an increase in accuracy. However, recent work has shown that the combination of graph attributes with GNN embeddings provides the biggest lift in accuracy.

The empirical correlation matrix of asset returns in an investment portfolio has its built-in noise due to market microstructure. This noise is usually eigenfiltered for robust risk analysis and management. Jacobi algorithm (JA) has been a popular eigensolver method due to its stability and efficient implementations. We present a fast FPGA implementation of parallel JA for noise filtering of empirical correlation matrix. Proposed FPGA implementation is compared with CPU and GPU implementations. It is shown that FPGA implementation of eigenfiltering operator in real-time significantly outperforms the others. We expect to see such emerging high performance DSP technologies to be widely used by the financial sector for real-time risk management and other tasks in the coming years.

In wireless ad hoc and sensor networks, energy is a scarce resource and a considerable amount of energy is dissipated due to interference. Therefore, interference is one of the major challenges in wireless ad hoc and sensor networks. It alters or disrupts a message as it is being transmitted along a channel between source and destination. Since the messages are disrupted when the interference occurs, they have to be detected and the interfered messages have to be retransmitted. In this paper, we propose central and distributed heuristic algorithms for reducing average interference in a receiver-centric interference model. In the literature, the minimum spanning tree (MST) algorithm is generally used through the interference coverage graph directly or indirectly in order to generate minimum average interference topology. Our algorithm, dynamic average interference (DAI), however, generates lower average interference as well as more sparse topology than MST. We realized that if the transmission ranges of nodes are taken into consideration at each stage of the topology control algorithm, the interference of links are changed dynamically. This interference changing enables up to 22% more energy saving than the MST algorithm. Thus, DAI provides energy saving by reducing the interference as far as possible in generated topology.