Aspect Root-Oriented Latent Structures with Graph Convolutional Networks for Aspect Sentiment Classification

The syntactic information of a dependency tree is an essential feature in relation extraction studies. Traditional dependency-based relation extraction methods can be categorized into hard pruning methods, which aim to remove unnecessary information, and soft pruning methods, which aim to utilize all lexical information. However, hard pruning has the potential to overlook important lexical information, while soft pruning can weaken the syntactic information between entities. As a result, recent studies in relation extraction have been shifting from dependency-based methods to pre-trained language model (LM) based methods. Nonetheless, LM-based methods increasingly demand larger language models and additional data. This trend leads to higher resource consumption, longer training times, and increased computational costs, yet often results in only marginal performance improvements. To address this problem, we propose a relation extraction model based on an entity-centric dependency tree: a dependency tree that is reconstructed by considering entities as root nodes. Using the entity-centric dependency tree, the proposed method can capture the syntactic information of an input sentence without losing lexical information. Additionally, we propose a novel model that utilizes entity-centric dependency trees in conjunction with language models, enabling efficient relation extraction without the need for additional data or larger models. In experiments with representative sentence-level relation extraction datasets such as TACRED, Re-TACRED, and SemEval 2010 Task 8, the proposed method achieves F1-scores of 74.9%, 91.2%, and 90.5%, respectively, which are state-of-the-art performances.

Incorporating biasing words obtained through contextual knowledge is paramount in automatic speech recognition (ASR) applications. This paper proposes an innovative method for achieving end-to-end contextual ASR using graph neural network (GNN) encodings based on the tree-constrained pointer generator method. GNN node encodings facilitate lookahead for future word pieces in the process of ASR decoding at each tree node by incorporating information about all word pieces on the tree branches rooted from it. This results in a more precise prediction of the generation probability of the biasing words. The study explores three GNN encoding techniques: namely the tree recursive neural network (Tree-RNN), the graph convolutional network (GCN), and GraphSAGE, along with different combinations of the complementary GCN and GraphSAGE structures. The performance of the systems was evaluated using both Librispeech and the AMI corpus with a visual-grounded contextual ASR pipeline. The findings indicate that using GNN encodings achieved consistent and significant reductions in word error rate (WER), particularly for words that are rare or have not been seen during the training process. Notably, on LibriSpeech test sets, the combined GNN proposed in this paper achieved a 20% relative rare word error rate reduction compared to Tree-RNN, 30%-40% compared to standard TCPGen and 60% compared to standard ASR systems without TCPGen.

Semantic information and syntactic information are two essential dimensions of language. In recent years, most researches focus on extracting semantic information or how to extract useful information from syntactic dependency tree. As the semantic representations are closely related to syntactic ones, how to effectively integrate semantic and syntactic information is still a subject worth studying. We propose attention mechanism based on graph convolutional networks. The model integrates syntactic dependence information into semantic features and automatically achieve a balance between semantic information and syntactic information. We conducted experiments on the task of sentence-level relation extraction, and the results show that our model performs better than some previous methods.

SK-GCN: Modeling Syntax and Knowledge via Graph Convolutional Network for aspect-level sentiment classification

Sex classification is a major benchmark of previous work in learning on the structural connectome, a naturally occurring brain graph that has proven useful for studying cognitive function and impairment. While graph neural networks (GNNs), specifically graph convolutional networks (GCNs), have gained popularity lately for their effectiveness in learning on graph data, achieving strong performance in adult sex classification tasks, their application to pediatric populations remains unexplored. We seek to characterize the capacity for GNN models to learn connectomic patterns on pediatric data through an exploration of training techniques and architectural design choices. Two datasets comprising an adult BRIGHT dataset (N = 147 Hodgkin's lymphoma survivors and N = 162 age similar controls) and a pediatric Human Connectome Project in Development (HCP-D) dataset (N = 135 healthy subjects) were utilized. Two GNN models (GCN simple and GCN residual), a deep neural network (multi-layer perceptron), and two standard machine learning models (random forest and support vector machine) were trained. Architecture exploration experiments were conducted to evaluate the impact of network depth, pooling techniques, and skip connections on the ability of GNN models to capture connectomic patterns. Models were assessed across a range of metrics including accuracy, AUC score, and adversarial robustness. GNNs outperformed other models across both populations. Notably, adult GNN models achieved 85.1% accuracy in sex classification on unseen adult participants, consistent with prior studies. The extension of the adult models to the pediatric dataset and training on the smaller pediatric dataset were sub-optimal in their performance. Using adult data to augment pediatric models, the best GNN achieved comparable accuracy across unseen pediatric (83.0%) and adult (81.3%) participants. Adversarial sensitivity experiments showed that the simple GCN remained the most robust to perturbations, followed by the multi-layer perceptron and the residual GCN. These findings underscore the potential of GNNs in advancing our understanding of sex-specific neurological development and disorders and highlight the importance of data augmentation in overcoming challenges associated with small pediatric datasets. Further, they highlight relevant tradeoffs in the design landscape of connectomic GNNs. For example, while the simpler GNN model tested exhibits marginally worse accuracy and AUC scores in comparison to the more complex residual GNN, it demonstrates a higher degree of adversarial robustness.

Background/Objective: The shift from classical rule-based and statistical systems of Machine Translation (MT) to more advanced Neural Machine Translation (NMT) systems employing transformers is quite astonishing. Still, translating language pairs such as English and Amharic, which are structurally different, poses a considerable challenge. This study explores the impact of incorporating known syntactic information on the performance of English-Amharic translation in Graph2Seq model to the precision and fluency of translations. Methods: We aimed to enhance translation performance with the design of an attention-based Graph2Seq model that utilizes a shaped syntactic dependency tree and implements Graph Neural Networks (GNN) to capture the hierarchy of language. The model overcomes the constraints posed by conventional sequence-to-sequence (Seq2Seq) models by adding syntactic information into the encoder. The dataset includes roughly 1.14 million parallel sentences in English and Amharic. Findings: There is a positive, actionable gap, as the proposed model was able to exceed the benchmarks set by the transformer models and pretrained methodologies, attaining BLEU 37.3, and demonstrating marked improvement in translation quality. Furthermore, these findings have defied the argument stating that diversity on the morpho-syntactic level impedes translation, instead illustrating the potency of rich superset syntax modeling. This score beats baseline figures by 4.56 points and 24.24 points compared to M2M100 and the standard transformer models, respectively. Novelty: All these points towards the fact that incorporating deep syntactic structures to enrich Graph-NMT systems on low-resource languages enhances their capabilities, paving avenues for further investigations in the field of Machine Translation. This study can be a starting point towards more research on the enhancement of accuracy and fluency of translations using a multidisciplinary approach based on language. Keywords: Graph neural networks, English-Amharic machine translation, Syntactic of source language, BLEU score, Low-resource language

Short text classification task is a special kind of text classification task in that the text to be classified is generally short, typically generating a sparse text representation that lacks rich semantic information. Given this shortcoming, scholars worldwide have explored improved short text classification methods based on deep learning. However, existing methods cannot effectively use concept knowledge and long-distance word dependencies. Therefore, based on graph neural networks from the perspective of text composition, we propose concept and dependencies enhanced graph convolutional networks for short text classification. First, the co-occurrence relationship between words is obtained by sliding window, the inclusion relationship between documents and words is obtained by TF-IDF, long-distance word dependencies is obtained by Stanford CoreNLP, and the association relationship between concepts in the concept graph with entities in the text is obtained through Microsoft Concept Graph. Then, a text graph is constructed for an entire text corpus based on the four relationships. Finally, the text graph is input into graph convolutional neural networks, and the category of each document node is predicted after two layers of convolution. Experimental results demonstrate that our proposed method overall best on multiple classical English text classification datasets.

Aspect-based sentiment analysis is a fine-grained task where the key goal is to predict sentiment polarities of one or more aspects in a given sentence. Currently, graph neural network models built upon dependency trees are widely employed for aspect-based sentiment analysis tasks. However, most existing models still contain a large amount of noisy nodes that cannot precisely capture the contextual relationships between specific aspects. Meanwhile, most studies do not consider the connections between nodes without direct dependency edges but play critical roles in determining the sentiment polarity of an aspect. To address the aforementioned limitations, we propose a Structured Dependency Tree-based Graph Convolutional Network (SDTGCN) model. Specifically, we explore construction of a structured syntactic dependency graph by incorporating positional information, sentiment commonsense knowledge, part-of-speech tags, syntactic dependency distances, etc., to assign arbitrary edge weights between nodes. This enhances the connections between aspect nodes and pivotal words while weakening irrelevant node links, enabling the model to sufficiently express sentiment dependencies between specific aspects and contextual information. We utilize part-of-speech tags and dependency distances to discover relationships between pivotal nodes without direct dependencies. Finally, we aggregate node information by fully considering their importance to obtain precise aspect representations. Experimental results on five publicly available datasets demonstrate the superiority of our proposed model over state-of-the-art approaches; furthermore, the accuracy and F1-score show a significant improvement on the majority of datasets, with increases of 0.74, 0.37, 0.65, and 0.79, 0.75, 1.17, respectively. This series of enhancements highlights the effective progress made by the STDGCN model in enhancing sentiment classification performance.

The n-octanol/buffer solution distribution coefficient at pH = 7.4 (log D7.4) is an indicator of lipophilicity, and it influences a wide variety of absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties and druggability of compounds. In log D7.4 prediction, graph neural networks (GNNs) can uncover subtle structure-property relationships (SPRs) by automatically extracting features from molecular graphs that facilitate the learning of SPRs, but their performances are often limited by the small size of available datasets. Herein, we present a transfer learning strategy called pretraining on computational data and then fine-tuning on experimental data (PCFE) to fully exploit the predictive potential of GNNs. PCFE works by pretraining a GNN model on 1.71 million computational log D data (low-fidelity data) and then fine-tuning it on 19,155 experimental log D7.4 data (high-fidelity data). The experiments for three GNN architectures (graph convolutional network (GCN), graph attention network (GAT), and Attentive FP) demonstrated the effectiveness of PCFE in improving GNNs for log D7.4 predictions. Moreover, the optimal PCFE-trained GNN model (cx-Attentive FP, Rtest2 = 0.909) outperformed four excellent descriptor-based models (random forest (RF), gradient boosting (GB), support vector machine (SVM), and extreme gradient boosting (XGBoost)). The robustness of the cx-Attentive FP model was also confirmed by evaluating the models with different training data sizes and dataset splitting strategies. Therefore, we developed a webserver and defined the applicability domain for this model. The webserver (http://tools.scbdd.com/chemlogd/) provides free log D7.4 prediction services. In addition, the important descriptors for log D7.4 were detected by the Shapley additive explanations (SHAP) method, and the most relevant substructures of log D7.4 were identified by the attention mechanism. Finally, the matched molecular pair analysis (MMPA) was performed to summarize the contributions of common chemical substituents to log D7.4, including a variety of hydrocarbon groups, halogen groups, heteroatoms, and polar groups. In conclusion, we believe that the cx-Attentive FP model can serve as a reliable tool to predict log D7.4 and hope that pretraining on low-fidelity data can help GNNs make accurate predictions of other endpoints in drug discovery.

Graph neural networks (GNNs) is an information - processing system that uses message passing among graph nodes. In recent years, GNN variants including graph attention network (GAT), graph convolutional network (GCN), and graph recurrent network (GRN) have shown revolutionary performance in computer vision applications using deep learning and artificial intelligence. These neural network model extensions, collect information in the form of graphs. GNN may be divided into three groups based on the challenges it solves: link prediction, node classification, graph classification. Machines can differentiate and recognise objects in image and video using standard CNNs. Extensive amount of research work needs to be done before robots can have same visual intuition as humans. GNN architectures, on the other hand, may be used to solve various image categorization and video challenges. The number of GNN applications in computer vision not limited, continues to expand. Human-object interaction, actin understanding, image categorization from a few shots and many more. In this paper use of GNN in image and video understanding, design aspects, architecture, applications and implementation challenges towards computer vision is described. GNN is a strong tool for analysing graph data and is still a relatively active area that needs further researches attention to solve many computer vision applications.

Learning node representations against perturbations

The power terminal detection system is an important part of the power system. It is of great significance to improve the intelligence of the power detection system to maintain the safety of the power system. However, the existing detection system relies more on traditional methods, which reduces the intelligence and accuracy of the detection system. Based on this, this paper proposes a power terminal detection method based on graph neural network. Firstly, the network flow data is used to model the power system as a node with no feature but sideband feature graph. Then, the graph neural network is used to iteratively learn the vector representation of each node in the communication topology according to the features of edges in the graph. Finally, nodes are classified according to the vector representation, so as to detect the vulnerabilities in the power system. When learning node representation, the proposed method considers the flow characteristics of power system and the communication topology of power system at the same time, and clearly considers the direction of edges in the graph. In addition, the proposed method is inductive, so it can adapt to the dynamic changes of power system. Experimental results on two public datasets show that the proposed method can converge quickly during training, and the Micro-F1 score of the proposed method is higher than that of the model that cannot use the power system communication topology information. Compared with other methods, the proposed method is easier to generalize to the unseen data during training.

AI-Driven molecule generation and bioactivity prediction: A multi-model approach combining VAE, graph and language-based neural networks.

The study of graph neural networks has revealed that they can unleash new applications in a variety of disciplines using such a basic process that we cannot imagine in the context of other deep learning designs. Many limitations limit their expressiveness, and researchers are working to overcome them to fully exploit the power of graph data. There are a number of publications that explore graph neural networks (GNNs) restrictions and bottlenecks, but the common thread that runs through them all is that they can all be traced back to message passing, which is the key technique we use to train our graph models. We outline the general GNN design pipeline in this study as well as discuss solutions to the over-smoothing problem, categorize the solutions, and identify open challenges for further research. Abbreviations: CGNN: Continuous Graph Neural Networks; CNN: Convolution NeuralNetwork; DeGNN: Decomposition Graph Neural Network; DGN: Directional GraphNetworks; DGN: Differentiable Group Normalization; DL: Deep Learning; EGAI:Enhancing GNNs by a High-quality Aggregation of Beneficial Information; GAT: GraphAttention Network; GCN: Graph Convolutional Network; GDC: Graph Drop Connect; GDR: Group Distance Ratio; GNN: Graph Neural Network; GRAND: GraphRandom Neural Networks; IIG: Instance Information Gain; MAD: Man AverageDistance; PDE-GCN: Partial Differential Equations-GCN; PTDNet: ParameterizedTopological Denoising network; TDGNN: Tree Decomposition Graph NeuralNetwork;

Aspect-based sentiment analysis (ABSA) aims to identify the sentiment polarity associated with specific aspect terms within sentences. Existing studies have primarily focused on constructing graphs from dependency trees of sentences to extract syntactic features. However, given that public datasets are often derived from online reviews, the syntactic structures of these sentences frequently exhibit irregularities. As a result, the performance of syntactic-based Graph Convolution Network (GCN) models is adversely impacted by the noise introduced during dependency parsing. Moreover, the interaction between syntactic and semantic information in these approaches is often insufficient, which significantly impairs the model's ability to accurately detect sentiment.To address these challenges, we propose a novel approach called Syntactic Denoising with Multi-strategy Auxiliary Enhancement (SDMAE) for the ABSA task. Specifically, we prune the original dependency tree by focusing on context words with specific part-of-speech features that are critical for conveying the sentiment of aspect terms, and then construct the graph. We introduce a Multi-channel Adaptive Aggregation Module (MAAM), a feature aggregation system that employs a multi-head attention mechanism to integrate semantic and syntactic GCN output representations. Furthermore, we design a multi-strategy task learning framework that incorporates sentiment lexicons and supervised contrastive learning to enhance the model's performance in aspect sentiment recognition.Comprehensive experiments conducted on four benchmark datasets demonstrate that our approach achieves significant performance improvements compared to several state-of-the-art methods across all evaluated datasets.