MR-zero meets RARE MRI: Joint optimization of refocusing flip angles and neural networks to minimize T2 -induced blurring in spin echo sequences.

PURPOSE: An end-to-end differentiable 2D Bloch simulation is used to reduce T2 induced blurring in single-shot turbo spin echo sequences, also called rapid imaging with refocused echoes (RARE) sequences, by using a joint optimization of refocusing flip angles and a convolutional neural network. METHODS: Simulation and optimization were performed in the MR-zero framework. Variable flip angle train and DenseNet parameters were optimized jointly using the instantaneous transverse magnetization, available in our simulation, at a certain echo time, which serves as ideal blurring-free target. Final optimized sequences were exported for in vivo measurements at a real system (3 T Siemens, PRISMA) using the Pulseq standard. RESULTS: The optimized RARE was able to successfully lower T2 -induced blurring for single-shot RARE sequences in proton density-weighted and T2 -weighted images. In addition to an increased sharpness, the neural network allowed correction of the contrast changes to match the theoretical transversal magnetization. The optimization found flip angle design strategies similar to existing literature, however, visual inspection of the images and evaluation of the respective point spread function demonstrated an improved performance. CONCLUSIONS: This work demonstrates that when variable flip angles and a convolutional neural network are optimized jointly in an end-to-end approach, sequences with more efficient minimization of T2 -induced blurring can be found. This allows faster single- or multi-shot RARE MRI with longer echo trains.

Weighted deep factorizing heterogeneous molecular network for genome-phenome association prediction.

Genome-phenome association (GPA) prediction can promote the understanding of biological mechanisms about complex pathology of phenotypes (i.e., traits and diseases). Traditional heterogeneous network-based GPA approaches overwhelmingly need to project heterogeneous data toward homogeneous network for data fusion and prediction, such projections result in the loss of heterogeneous network structure information. Matrix factorization based data fusion can avoid such projection by integrating multi-type data in a coherent way, but they typically perform linear factorization and cannot mine the nonlinear relationships between molecules, which compromise the accuracy of GPA analysis. Furthermore, most of them can not selectively synergy network topology and node attribution information in a principle way. In this paper, we propose a weighted deep matrix factorization based solution (WDGPA) to predict GPAs by selectively and differentially fusing heterogeneous molecular network and diverse attributes of nodes. WDGPA firstly assigns weights to inter/intra-relational data matrices and attribute data matrices, and performs deep matrix factorization on these matrices of heterogeneous network in a cooperative manner to obtain the nonlinear representations of different nodes. In addition, it performs low-rank representation learning on the attribute data with the shared nonlinear representations. In this way, both the network topology and node attributes are jointly mined to explore the representations of molecules and complex interplays between molecules and phenotypes. WDGPA then uses the representational vectors of gene and phenotype nodes to predict GPAs. Experimental results on maize and human datasets confirm that WDGPA outperforms competitive methods by a large margin under different evaluation protocols.

JUTAR: Joint User-Association, Task-Partition, and Resource-Allocation Algorithm for MEC Networks.

Mobile edge computing (MEC) is a promising technique to support the emerging delay-sensitive and compute-intensive applications for user equipment (UE) by means of computation offloading. However, designing a computation offloading algorithm for the MEC network to meet the restrictive requirements towards system latency and energy consumption remains challenging. In this paper, we propose a joint user-association, task-partition, and resource-allocation (JUTAR) algorithm to solve the computation offloading problem. In particular, we first build an optimization function for the computation offloading problem. Then, we utilize the user association and smooth approximation to simplify the objective function. Finally, we employ the particle swarm algorithm (PSA) to find the optimal solution. The proposed JUTAR algorithm achieves a better system performance compared with the state-of-the-art (SOA) computation offloading algorithm due to the joint optimization of the user association, task partition, and resource allocation for computation offloading. Numerical results show that, compared with the SOA algorithm, the proposed JUTAR achieves about 21% system performance gain in the MEC network with 100 pieces of UE.

Joint Data Transmission and Energy Harvesting for MISO Downlink Transmission Coordination in Wireless IoT Networks.

The advent of simultaneous wireless information and power (SWIPT) has been regarded as a promising technique to provide power supplies for an energy sustainable Internet of Things (IoT), which is of paramount importance due to the proliferation of high data communication demands of low-power network devices. In such networks, a multi-antenna base station (BS) in each cell can be utilized to concurrently transmit messages and energies to its intended IoT user equipment (IoT-UE) with a single antenna under a common broadcast frequency band, resulting in a multi-cell multi-input single-output (MISO) interference channel (IC). In this work, we aim to find the trade-off between the spectrum efficiency (SE) and energy harvesting (EH) in SWIPT-enabled networks with MISO ICs. For this, we derive a multi-objective optimization (MOO) formulation to obtain the optimal beamforming pattern (BP) and power splitting ratio (PR), and we propose a fractional programming (FP) model to find the solution. To tackle the nonconvexity of FP, an evolutionary algorithm (EA)-aided quadratic transform technique is proposed, which recasts the nonconvex problem as a sequence of convex problems to be solved iteratively. To further reduce the communication overhead and computational complexity, a distributed multi-agent learning-based approach is proposed that requires only partial observations of the channel state information (CSI). In this approach, each BS is equipped with a double deep Q network (DDQN) to determine the BP and PR for its UE with lower computational complexity based on the observations through a limited information exchange process. Finally, with the simulation experiments, we verify the trade-off between SE and EH, and we demonstrate that, apart from the FP algorithm introduced to provide superior solutions, the proposed DDQN algorithm also shows its performance gain in terms of utility to be up to 1.23-, 1.87-, and 3.45-times larger than the Advantage Actor Critic (A2C), greedy, and random algorithms, respectively, in comparison in the simulated environment.

Federated Learning Based Fault Diagnosis Driven by Intra-Client Imbalance Degree.

Federated learning is an effective means to combine model information from different clients to achieve joint optimization when the model of a single client is insufficient. In the case when there is an inter-client data imbalance, it is significant to design an imbalanced federation aggregation strategy to aggregate model information so that each client can benefit from the federation global model. However, the existing method has failed to achieve an efficient federation strategy in the case when there is an imbalance mode mismatch between clients. This paper aims to design a federated learning method guided by intra-client imbalance degree to ensure that each client can receive the maximum benefit from the federation model. The degree of intra-client imbalance, measured by gain of a class-by-class model update on the federation model based on a small balanced dataset, is used to guide the designing of federation strategy. An experimental validation for the benchmark dataset of rolling bearing shows that a 23.33% improvement of fault diagnosis accuracy can be achieved in the case when the degree of imbalance mode mismatch between clients is prominent.

Joint reconstruction of neuron and ultrastructure via connectivity consensus in electron microscope volumes.

BACKGROUND: Nanoscale connectomics, which aims to map the fine connections between neurons with synaptic-level detail, has attracted increasing attention in recent years. Currently, the automated reconstruction algorithms in electron microscope volumes are in great demand. Most existing reconstruction methodologies for cellular and subcellular structures are independent, and exploring the inter-relationships between structures will contribute to image analysis. The primary goal of this research is to construct a joint optimization framework to improve the accuracy and efficiency of neural structure reconstruction algorithms. RESULTS: In this investigation, we introduce the concept of connectivity consensus between cellular and subcellular structures based on biological domain knowledge for neural structure agglomeration problems. We propose a joint graph partitioning model for solving ultrastructural and neuronal connections to overcome the limitations of connectivity cues at different levels. The advantage of the optimization model is the simultaneous reconstruction of multiple structures in one optimization step. The experimental results on several public datasets demonstrate that the joint optimization model outperforms existing hierarchical agglomeration algorithms. CONCLUSIONS: We present a joint optimization model by connectivity consensus to solve the neural structure agglomeration problem and demonstrate its superiority to existing methods. The intention of introducing connectivity consensus between different structures is to build a suitable optimization model that makes the reconstruction goals more consistent with biological plausible and domain knowledge. This idea can inspire other researchers to optimize existing reconstruction algorithms and other areas of biological data analysis.

Two-Step Joint Optimization with Auxiliary Loss Function for Noise-Robust Speech Recognition.

In this paper, a new two-step joint optimization approach based on the asynchronous subregion optimization method is proposed for training a pipeline model composed of two different models. The first-step processing of the proposed joint optimization approach trains the front-end model only, and the second-step processing trains all the parameters of the combined model together. In the asynchronous subregion optimization method, the first-step processing only supports the goal of the front-end model. However, the first-step processing of the proposed approach works with a new loss function to make the front-end model support the goal of the back-end model. The proposed optimization approach was applied, here, to a pipeline composed of a deep complex convolutional recurrent network (DCCRN)-based speech enhancement model and a conformer-transducer-based ASR model as a front-end and a back-end, respectively. Then, the performance of the proposed two-step joint optimization approach was evaluated on the LibriSpeech automatic speech recognition (ASR) corpus in noisy environments by measuring the character error rate (CER) and word error rate (WER). In addition, an ablation study was carried out to examine the effectiveness of the proposed optimization approach on each of the processing blocks in the conformer-transducer ASR model. Consequently, it was shown from the ablation study that the conformer-transducer-based ASR model with the joint network trained only by the proposed optimization approach achieved the lowest average CER and WER. Moreover, the proposed optimization approach reduced the average CER and WER on the Test-Noisy dataset under matched noise conditions by 0.30% and 0.48%, respectively, compared to the approach of separate optimization of speech enhancement and ASR. Compared to the conventional two-step joint optimization approach, the proposed optimization approach provided average CER and WER reductions of 0.22% and 0.31%, respectively. Moreover, it was revealed that the proposed optimization approach achieved a lower average CER and WER, by 0.32% and 0.43%, respectively, than the conventional optimization approach under mismatched noise conditions.

Secrecy Capacity Maximization of UAV-Enabled Relaying Systems with 3D Trajectory Design and Resource Allocation.

Unmanned aerial vehicles (UAVs) have attracted considerable attention, thanks to their high flexibility, on-demand deployment and the freedom in trajectory design. The communication channel quality can be effectively improved by using UAV to build a line-of-sight communication link between the transmitter and the receiver. Furthermore, there is increasing demand for communication security improvement, as the openness of a wireless channel brings serious threat. This paper formulates a secrecy capacity optimization problem of a UAV-enabled relay communication system in the presence of malicious eavesdroppers, in which the secrecy capacity is maximized by jointly optimizing the UAV relay's location, power allocation, and bandwidth allocation under the communication quality and information causality constraints. A successive convex approximation-alternative iterative optimization (SCA-AIO) algorithm is proposed to solve this highly coupled nonconvex problem. Simulation results demonstrate the superiority of the proposed secrecy transmission strategy with optimal trajectory design and resource allocation compared with the benchmark schemes and reveal the impacts of communication resources on system performance.

Joint Beamforming, Power Allocation, and Splitting Control for SWIPT-Enabled IoT Networks with Deep Reinforcement Learning and Game Theory.

Future wireless networks promise immense increases on data rate and energy efficiency while overcoming the difficulties of charging the wireless stations or devices in the Internet of Things (IoT) with the capability of simultaneous wireless information and power transfer (SWIPT). For such networks, jointly optimizing beamforming, power control, and energy harvesting to enhance the communication performance from the base stations (BSs) (or access points (APs)) to the mobile nodes (MNs) served would be a real challenge. In this work, we formulate the joint optimization as a mixed integer nonlinear programming (MINLP) problem, which can be also realized as a complex multiple resource allocation (MRA) optimization problem subject to different allocation constraints. By means of deep reinforcement learning to estimate future rewards of actions based on the reported information from the users served by the networks, we introduce single-layer MRA algorithms based on deep Q-learning (DQN) and deep deterministic policy gradient (DDPG), respectively, as the basis for the downlink wireless transmissions. Moreover, by incorporating the capability of data-driven DQN technique and the strength of noncooperative game theory model, we propose a two-layer iterative approach to resolve the NP-hard MRA problem, which can further improve the communication performance in terms of data rate, energy harvesting, and power consumption. For the two-layer approach, we also introduce a pricing strategy for BSs or APs to determine their power costs on the basis of social utility maximization to control the transmit power. Finally, with the simulated environment based on realistic wireless networks, our numerical results show that the two-layer MRA algorithm proposed can achieve up to 2.3 times higher value than the single-layer counterparts which represent the data-driven deep reinforcement learning-based algorithms extended to resolve the problem, in terms of the utilities designed to reflect the trade-off among the performance metrics considered.

End-to-End Model-Based Detection of Infants with Autism Spectrum Disorder Using a Pretrained Model.

In this paper, we propose an end-to-end (E2E) neural network model to detect autism spectrum disorder (ASD) from children's voices without explicitly extracting the deterministic features. In order to obtain the decisions for discriminating between the voices of children with ASD and those with typical development (TD), we combined two different feature-extraction models and a bidirectional long short-term memory (BLSTM)-based classifier to obtain the ASD/TD classification in the form of probability. We realized one of the feature extractors as the bottleneck feature from an autoencoder using the extended version of the Geneva minimalistic acoustic parameter set (eGeMAPS) input. The other feature extractor is the context vector from a pretrained wav2vec2.0-based model directly applied to the waveform input. In addition, we optimized the E2E models in two different ways: (1) fine-tuning and (2) joint optimization. To evaluate the performance of the proposed E2E models, we prepared two datasets from video recordings of ASD diagnoses collected between 2016 and 2018 at Seoul National University Bundang Hospital (SNUBH), and between 2019 and 2021 at a Living Lab. According to the experimental results, the proposed wav2vec2.0-based E2E model with joint optimization achieved significant improvements in the accuracy and unweighted average recall, from 64.74% to 71.66% and from 65.04% to 70.81%, respectively, compared with a conventional model using autoencoder-based BLSTM and the deterministic features of the eGeMAPS.

Distributed Joint Optimization of Beamforming and PowerAllocation for Maximizing the Energy Efficiency of CognitiveHeterogeneous Networks.

This paper investigated an energy-efficient beamforming and power allocation strategy for cognitive heterogeneous networks with multiple-input-single-output interference channels. To maximize the sum energy efficiency of secondary users (SUs) while keeping the interference to primary networks under a predetermined threshold, I propose a distributed resource allocation algorithm using dual methods, in which each SU updates its beamforming vector and transmit power iteratively without any information sharing until convergence. The simulation results verify that the performance of the proposed scheme is comparable to that of the optimal scheme but with a much shorter computation time.

A Marine Organism Detection Framework Based on the Joint Optimization of Image Enhancement and Object Detection.

Underwater vision-based detection plays an increasingly important role in underwater security, ocean exploration and other fields. Due to the absorption and scattering effects of water on light, as well as the movement of the carrier, underwater images generally have problems such as noise pollution, color cast and motion blur, which seriously affect the performance of underwater vision-based detection. To address these problems, this study proposes an end-to-end marine organism detection framework that can jointly optimize the image enhancement and object detection. The framework uses a two-stage detection network with dynamic intersection over union (IoU) threshold as the backbone and adds an underwater image enhancement module (UIEM) composed of denoising, color correction and deblurring sub-modules to greatly improve the framework's ability to deal with severely degraded underwater images. Meanwhile, a self-built dataset is introduced to pre-train the UIEM, so that the training of the entire framework can be performed end-to-end. The experimental results show that compared with the existing end-to-end models applied to marine organism detection, the detection precision of the proposed framework can improve by at least 6%, and the detection speed has not been significantly reduced, so that it can complete the high-precision real-time detection of marine organisms.

Novel Cooperative Scheme Based on Joint Band Assignment and Power Allocation for a Coexisting Radar-Communications System.

In this paper, we present a novel cooperative scheme of joint optimal resource allocation, such that the overall performance of the coexisting radar-communications (CRC) system can be improved. In our proposed scheme, target detection and multiuser communication are performed by radar and communication subsystems at the same time, as well as a control center, which is responsible for joint resource management. We aim to minimize the ISLR for target detection and maximize the sum-rate for communications simultaneously by jointly optimizing the band assignment and transmit power allocation. Since the resulting optimization problem involving two performance metrics and a binary constraint is a multiobjective nonconvex problem, a two-tier iterative decomposition (TT-ID) approach is devised to obtain the globally optimal solution. However, compared with the conventional radar signals, the autocorrelation function of the devised radar signal may still have relatively high sidelobes. In particular, when the data transmission becomes the primary purpose of the CRC system, the sidelobe performance gets worse. As a consequence, some weak targets are most likely overshadowed by the adjacent strong targets through the matched filtering at the radar receiver. To address this, a spectral estimation algorithm based on the Bayes Cauchy-Gaussian (Bayes-CG) model is employed to further reduce the range sidelobes of the matched filter output at the radar receiver according to the prior distribution of the desired autocorrelation. Finally, several numerical results are provided to show the merits of the proposed method.

Joint Maximum Likelihood of Phylogeny and Ancestral States Is Not Consistent.

Maximum likelihood estimation in phylogenetics requires a means of handling unknown ancestral states. Classical maximum likelihood averages over these unknown intermediate states, leading to provably consistent estimation of the topology and continuous model parameters. Recently, a computationally efficient approach has been proposed to jointly maximize over these unknown states and phylogenetic parameters. Although this method of joint maximum likelihood estimation can obtain estimates more quickly, its properties as an estimator are not yet clear. In this article, we show that this method of jointly estimating phylogenetic parameters along with ancestral states is not consistent in general. We find a sizeable region of parameter space that generates data on a four-taxon tree for which this joint method estimates the internal branch length to be exactly zero, even in the limit of infinite-length sequences. More generally, we show that this joint method only estimates branch lengths correctly on a set of measure zero. We show empirically that branch length estimates are systematically biased downward, even for short branches.

Joint Optimization of Deep Neural Network-Based Dereverberation and Beamforming for Sound Event Detection in Multi-Channel Environments.

In this paper, we propose joint optimization of deep neural network (DNN)-supported dereverberation and beamforming for the convolutional recurrent neural network (CRNN)-based sound event detection (SED) in multi-channel environments. First, the short-time Fourier transform (STFT) coefficients are calculated from multi-channel audio signals under the noisy and reverberant environments, which are then enhanced by the DNN-supported weighted prediction error (WPE) dereverberation with the estimated masks. Next, the STFT coefficients of the dereverberated multi-channel audio signals are conveyed to the DNN-supported minimum variance distortionless response (MVDR) beamformer in which DNN-supported MVDR beamforming is carried out with the source and noise masks estimated by the DNN. As a result, the single-channel enhanced STFT coefficients are shown at the output and tossed to the CRNN-based SED system, and then, the three modules are jointly trained by the single loss function designed for SED. Furthermore, to ease the difficulty of training a deep learning model for SED caused by the imbalance in the amount of data for each class, the focal loss is used as a loss function. Experimental results show that joint training of DNN-supported dereverberation and beamforming with the SED model under the supervision of focal loss significantly improves the performance under the noisy and reverberant environments.

Deep-Learning-Based Detection of Infants with Autism Spectrum Disorder Using Auto-Encoder Feature Representation.

Autism spectrum disorder (ASD) is a developmental disorder with a life-span disability. While diagnostic instruments have been developed and qualified based on the accuracy of the discrimination of children with ASD from typical development (TD) children, the stability of such procedures can be disrupted by limitations pertaining to time expenses and the subjectivity of clinicians. Consequently, automated diagnostic methods have been developed for acquiring objective measures of autism, and in various fields of research, vocal characteristics have not only been reported as distinctive characteristics by clinicians, but have also shown promising performance in several studies utilizing deep learning models based on the automated discrimination of children with ASD from children with TD. However, difficulties still exist in terms of the characteristics of the data, the complexity of the analysis, and the lack of arranged data caused by the low accessibility for diagnosis and the need to secure anonymity. In order to address these issues, we introduce a pre-trained feature extraction auto-encoder model and a joint optimization scheme, which can achieve robustness for widely distributed and unrefined data using a deep-learning-based method for the detection of autism that utilizes various models. By adopting this auto-encoder-based feature extraction and joint optimization in the extended version of the Geneva minimalistic acoustic parameter set (eGeMAPS) speech feature data set, we acquire improved performance in the detection of ASD in infants compared to the raw data set.

Autocalibrated wave-CAIPI reconstruction; Joint optimization of k-space trajectory and parallel imaging reconstruction.

PURPOSE: Fast MRI acquisitions often rely on efficient traversal of k-space and hardware limitations, or other physical effects can cause the k-space trajectory to deviate from a theoretical path in a manner dependent on the image prescription and protocol parameters. Additional measurements or generalized calibrations are typically needed to characterize the discrepancies. We propose an autocalibrated technique to determine these discrepancies. METHODS: A joint optimization is used to estimate the trajectory simultaneously with the parallel imaging reconstruction, without the need for additional measurements. Model reduction is introduced to make this optimization computationally efficient, and to ensure final image quality. RESULTS: We demonstrate our approach for the wave-CAIPI fast acquisition method that uses a corkscrew k-space path to efficiently encode k-space and spread the voxel aliasing. Model reduction allows for the 3D trajectory to be automatically calculated in fewer than 30 s on standard vendor hardware. The method achieves equivalent accuracy to full-gradient calibration scans. CONCLUSIONS: The proposed method allows for high-quality wave-CAIPI reconstruction across wide ranges of protocol parameters, such as field of view (FOV) location/orientation, bandwidth, echo time (TE), resolution, and sinusoidal amplitude/frequency. Our framework should allow for the autocalibration of gradient trajectories from many other fast MRI techniques in clinically relevant time. Magn Reson Med 78:1093-1099, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Joint optimization of degradation assessment and remaining useful life prediction for bearings with temporal convolutional auto-encoder.

Remaining useful life (RUL) prediction and degradation assessment are pivotal components of prognostic and health management (PHM) and represent vital tasks in the implementation of predictive maintenance for bearings. In recent years, data-driven PHM techniques for bearings have made substantial progress through the integration of deep learning methods. However, modeling the temporal dependencies inherent in raw vibration signals for both degradation assessment and RUL prediction remains a significant challenge. Hence, we propose a joint optimization architecture that uses a temporal convolutional auto-encoder (TCAE) for the degradation assessment and RUL prediction of bearings. Specifically, the architecture includes a sequence-to-sequence model to extract degradation-sensitive features from the raw signal and utilizes temporal distribution characterization (TDC) and a nonlinear regressor to determine the degradation stages and predict RUL, respectively. Our framework integrates the tasks of degradation assessment and RUL prediction in a unified, end-to-end manner, using raw signals as input, resulting in high RUL prediction accuracy (RMSE = 0.0832) on publicly available and self-built datasets. Our approach outperforms state-of-the-art methods, indicating its potential to significantly advance the field of PHM for bearings.

Scalp surface estimation and head registration using sparse sampling and 3D statistical models.

Registering the head and estimating the scalp surface are important for various biomedical procedures, including those using neuronavigation to localize brain stimulation or recording. However, neuronavigation systems rely on manually-identified fiducial head targets and often require a patient-specific MRI for accurate registration, limiting adoption. We propose a practical technique capable of inferring the scalp shape and use it to accurately register the subject's head. Our method does not require anatomical landmark annotation or an individual MRI scan, yet achieves accurate registration of the subject's head and estimation of its surface. The scalp shape is estimated from surface samples easily acquired using existing pointer tools, and registration exploits statistical head model priors. Our method allows for the acquisition of non-trivial shapes from a limited number of data points while leveraging their object class priors, surpassing the accuracy of common reconstruction and registration methods using the same tools. The proposed approach is evaluated in a virtual study with head MRI data from 1152 subjects, achieving an average reconstruction root-mean-square error of 2.95 mm, which outperforms a common neuronavigation technique by 2.70 mm. We also characterize the error under different conditions and provide guidelines for efficient sampling. Furthermore, we demonstrate and validate the proposed method on data from 50 subjects collected with conventional neuronavigation tools and setup, obtaining an average root-mean-square error of 2.89 mm; adding landmark-based registration improves this error to 2.63 mm. The simulation and experimental results support the proposed method's effectiveness with or without landmark annotation, highlighting its broad applicability.

PIPER: A logic-driven deep contrastive optimization pipeline for event temporal reasoning.

Event temporal relation extraction is an important task for information extraction. The existing methods usually rely on feature engineering and require post-process to achieve optimization, though inconsistent optimization may occur in the post-process module and main neural network due to their independence. Recently, a few works start to incorporate the temporal logic rules into the neural network and achieve joint optimization. However, these methods still suffer from two shortcomings: (1) Although the joint optimization is applied, the differences between rules are neglected in the unified design of rule losses and further the interpretability and flexibility of the design of model are reduced. (2) Because of lacking abundant syntactic connections between events and rule-match features, the performance of the model may be suppressed by the inefficient interaction in training between features and rules. To tackle these issues, this paper proposes PIPER, a logic-driven deep contrastive optimization pipeline for event temporal reasoning. Specifically, we apply joint optimization (including multi-stage and single-stage joint paradigms) by combining independent rule losses (i.e., flexibility) to make PIPER more interpretable. Also, by proposing a hierarchical graph distillation network to obtain more abundant syntactic information, the designed rule-match features can effectively aid in the interaction between low-level features and high-level rules during training. The final experiments on TB-Dense and MATRES demonstrate that the proposed model can achieve competitive performance compared with the recent advances.