Search for: All records

Outlier detection (OD) is a key machine learning task for finding rare and deviant data samples, with many time-critical applications such as fraud detection and intrusion detection. In this work, we propose TOD, the first tensor-based system for efficient and scalable outlier detection on distributed multi-GPU machines. A key idea behind TOD is decomposing complex OD applications into a small collection of basic tensor algebra operators. This decomposition enables TOD to accelerate OD computations by leveraging recent advances in deep learning infrastructure in both hardware and software. Moreover, to deploy memory-intensive OD applications on modern GPUs with limited on-device memory, we introduce two key techniques. First, provable quantization speeds up OD computations and reduces its memory footprint by automatically performing specific floating-point operations in lower precision while provably guaranteeing no accuracy loss. Second, to exploit the aggregated compute resources and memory capacity of multiple GPUs, we introduce automatic batching , which decomposes OD computations into small batches for both sequential execution on a single GPU and parallel execution across multiple GPUs. TOD supports a diverse set of OD algorithms. Evaluation on 11 real-world and 3 synthetic OD datasets shows that TOD is on average 10.9X faster than the leading CPU-based OD system PyOD (with a maximum speedup of 38.9X), and can handle much larger datasets than existing GPU-based OD systems. In addition, TOD allows easy integration of new OD operators, enabling fast prototyping of emerging and yet-to-discovered OD algorithms. 

This paper applies a common-mode modeling approach for a Silicon Carbide (SiC) based medium voltage neutral point clamped (NPC) dual active bridge (DAB) with a 2 level Full-Bridge (2L-FB) stage utilizing an electromagnetic interference (EMI) characterization testbed. A common-mode equivalent circuit model (CEM) for the system is derived, which accurately captures the effect of cross-mode coupling behavior between differential-mode and common-mode caused by circuit asymmetries, such as baseplate capacitance of multi-chip power modules or windings in the transformer. This cross-mode coupling effect is required to accurately model EMI at the higher frequencies of the conducted emissions standards. The derived CEM shows close agreement when compared to the mixed-mode simulation, verifying the model's efficacy. Additionally, baseplate current was shown to be minimized by tying the neutral point of the converter to the heatsink, where this result can be explained through the CEM. The CEM of the NPC DAB will be validated through empirical measurements on an EMI characterization testbed. The testbed features a copper ground plane and custom-built LISNs that can handle the unfiltered harmonic and EMI content of power electronic converters. 

Attributed networks are a type of graph structured data used in many real-world scenarios. Detecting anomalies on attributed networks has a wide spectrum of applications such as spammer detection and fraud detection. Although this research area draws increasing attention in the last few years, previous works are mostly unsupervised because of expensive costs of labeling ground truth anomalies. Many recent studies have shown different types of anomalies are often mixed together on attributed networks and such invaluable human knowledge could provide complementary insights in advancing anomaly detection on attributed networks. To this end, we study the novel problem of modeling and integrating human knowledge of different anomaly types for attributed network anomaly detection. Specifically, we first model prior human knowledge through a novel data augmentation strategy. We then integrate the modeled knowledge in a Siamese graph neural network encoder through a well-designed contrastive loss. In the end, we train a decoder to reconstruct the original networks from the node representations learned by the encoder, and rank nodes according to its reconstruction error as the anomaly metric. Experiments on five real-world datasets demonstrate that the proposed framework outperforms the state-of-the-art anomaly detection algorithms.