Whole slide image (WSI) classification is one of the important fields of digital pathology, and is generally solved as a weakly supervised learning problem by adopting multiple instance learning (MIL). However, a common but crucial challenge faced by existing MIL models is their inability to provide convincing explanations that can win the trust of pathologists and be applied to clinical diagnosis. In addition, most attention-based MIL models use attention scores to represent the importance of each patch in the WSI rather than inferring patch probabilities directly, which does not accurately detect the critical patches. To address these two challenges, we propose a ProtoTree based MIL model for WSI classification, called ProtoTree-MIL, where ProtoTree is an interpretable model that combines the advantages of prototype-learning and decision tree. ProtoTree-MIL not only explains why some patches are important for the final prediction through prototype-learning, but also provides global and local explanation through decision tree. We also propose a method to infer patch probabilities and measure their importance under the framework of ProtoTree-MIL. By conducting various experiments on three public WSI datasets, Camelyon16, TCGA-NSCLC, and TCGA-RCC, we demonstrate that our proposed ProtoTree-MIL can achieve a competitive performance to the state-of-the-art MIL models but provide more persuasive explanations than them. Explicitly generating patch probabilities also makes ProtoTree-MIL more accurate to detect the key patches than other attention-based MIL models. Specially, by evaluating our model on a real clinical gastritis and gastric cancer dataset, we show the explanations provided by ProtoTree-MIL are significant and faithful.

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. Specifically, SEFraud achieves the most significant improvement with 8.6% on AUC and 8.5% on Recall over the second best on fraud detection, as well as an average of 10x speed-up regarding the inference time. Last but not least, 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.

Recently, neural networks based models have been widely used for recommender systems (RS). Unfortunately, the existing neural network based RS solutions are often treated as black-boxes, which gain little trust and confidence from users. Thus, there is an increasing demand of explainability. Several explainable recommendation methods have been introduced to RS. However, there is a trade-off between explainability and performance among these methods. In this paper, we propose a novel framework, the Tower Bridge Net (TB-Net), using the proposed bidirectional embedding propagation approach to achieve both superior recommendation and explainability performances. Extensive validation on three public datasets shows that the performance of TB-Net dominates the state-of-the-art models. We quantitatively evaluate the explainability by using numerical metrics and experimentally prove that TB-Net achieves a significant improvement on explainability compared with existing methods. More importantly, TB-Net has been deployed and offers explainable recommendation service for the largest bank in China, Industrial and Commercial Bank of China Limited (ICBC). Results on a billion-scale dataset (1.2 billion nodes and edges) from ICBC show that TB-Net can provide both accurate recommendations and semantic explanations, and is very effective and deployable in practice.

Deep learning has shown powerful performances in many fields, however its black-box nature hinders its further applications. In response, explainable artificial intelligence emerges, aiming to explain the predictions and behaviors of deep learning models. Among many explanation methods, counterfactual explanation has been identified as one of the best methods due to its resemblance to human cognitive process: to deliver an explanation by constructing a contrastive situation so that human may interpret the underlying mechanism by cognitively demonstrating the difference.

One of the major purposes for fifth generation (5G) communications waveform design is to relax the synchronization requirements for supporting efficient massive machine type communications (MTCs). Polynomial cancellation coded orthogonal frequency-division multiplexing (PCC-OFDM) and universal filtered multi-carrier (UFMC) are designed to reduce the sidelobes of the OFDM waveform to protect against intercarrier interference (ICI) in the 5G uplink. To the best of our knowledge, there is no analysis of the effect of ICI for the UFMC system with time offset transmissions that many arise in MTC scenarios. Furthermore, there is no study on reducing the computational complexity of the UFMC system. This paper provides closed-form expressions for time offsets interference in such a case for OFDM, PCC-OFDM, and UFMC. This paper also presents theoretical analysis for the signal-to-interference-plus-noise ratio, achievable rate, and bit error ratio performance. The results show that PCC-OFDM significantly protects against ICI at the cost of halving the spectral efficiency. UFMC improves the ICI and intersymbol interference protection performance, especially when the length of time offset is very small, at the cost of significantly increasing the computational complexity. Finally, this paper proposes the overlap and adds UFMC and a variant of UFMC using infinite impulse response prototype filter banks to reduce the processing complexity.

Machine type communications (MTC) could play a significant role in fifth generation (5G) wireless communications systems. In terms of reducing the side-lobes of orthogonal frequency-division multiplexing (OFDM) to support large numbers of asynchronous MTC devices, several waveform designs could be used. This paper provides closed form signal-to-interference-plus-noise ratio (SINR) and capacity results for this asynchronous scenario. We compare three candidate multi-carrier waveforms, which are OFDM, universal filtered multi-carrier (UFMC) and polynomial cancellation coded (PCC-OFDM). Our results indicate that both PCC and UFMC can provide better frequency roll-off than OFDM. PCC is more easier to implement and performs strongly against inter carrier interference (ICI) with cost of losing spectral efficiency and a higher peak-to-average power ratio (PAPR). UFMC is more robust to very dispersive multipath channels but with cost of increasing computational complexity.

With increasing demand for machine‐to‐machine (M2M) communications, modifying existing orthogonal frequency‐division multiple access communication systems such as the long‐term evolution (LTE) system to successfully support low‐data rate M2M devices has become an important issue. In LTE Release 12 and beyond, the reduction of maximum bandwidth, the reduction of transmission power and the reduction of downlink transmission model should be studied for supporting low‐data rate M2M communications. This paper will address one solution based on the virtual carrier (VC) concept, which aims to improve the bandwidth efficiency and cost‐efficiency, using analogue filters to extract only sub‐carriers of interest. This will reduce the sampling rate at the M2M analogue‐to‐digital converter (ADC) leading to improvements in ADC power consumption and the computational complexity. Our results indicate that the VC system can provide significant high signal‐to‐interference‐plus‐noise ratio performance without significant bit error rate degradation.

Machine-to-Machine (M2M) communications normally require low data transmission rates and low cost devices. Thus, how to modify existing cellular systems such as the Long Term Evolution (LTE) system to successfully support low cost M2M devices will become a major issue for industry. This paper will address one solution based on the virtual carrier system, which improves bandwidth efficiency and reduces the power dissipation dramatically on the LTE downlink. Our results indicate that the virtual carrier system provides a high Signal- to-Interference-and-Noise Ratio (SINR) performance without significant Bit Error Rate (BER) degradation.