The response behaviors observed in online user-generated content (UGC) frequently demonstrate non-linear characteristics, such as conditional branching and selective avoidance. These patterns present additional challenges for ensuring the trustworthiness of Large Language Model (LLMs) reasoning, particularly as their unidirectional, left-to-right inference mechanisms may not adequately capture such complex reasoning dynamics. To address this, we propose a Forest of Thought Explanation (FoTE), a novel prompting that models the selective avoidance in UGC while ensuring explanation consensus through reasoning paths across all decision sub-trees. FoTE firstly generates various reasoning paths through an adaptive CoT prompting. Each generated thought is subsequently evaluated through cooperative game theory to quantify its fair influence. The thoughts with the top-k contribution scores are preserved and randomly sampled to emulate selective avoidance for the next reasoning iteration. Through extensive evaluations across three open-source LLMs and two established social science problems (spanning four benchmark datasets), FoTE demonstrates superior success rates compared to competing prompting strategies. Notably, its performance gains increase with the strength of selective avoidance in social problems. The trustworthiness of our FoTE is enhanced by the incorporation of (1) a solid theoretical foundation and (2) a transparent reasoning path that converges toward consensus.

Existing solutions for bundle recommendation (BR) have achieved remarkable effectiveness for predicting the user’s preference for prebuilt bundles. However, bundle-item (B-I) affiliation will vary dynamically in real scenarios. For ex ample, a bundle themed as ‘casual outfit’ may add ‘hat’ or remove ‘watch’ due to factors such as seasonal variations, changes in user preferences or inventory adjustments. Our empirical study demonstrates that the performance of main stream BR models may fluctuate or decline under item-level variability. This paper makes the first attempt to address the above problem and proposes Residual Diffusion for Bundle Recommendation (RDiffBR) as a model-agnostic generative framework which can assist a BR model in adapting this sce nario. During the initial training of the BR model, RDiffBR employs a residual diffusion model to process the item-level bundle embeddings which are generated by the BR model to represent bundle theme via a forward-reverse process. In the inference stage, RDiffBR reverses item-level bundle em beddings obtained by the well-trained bundle model under B-I variability scenarios to generate the effective item-level bundle embeddings. In particular, the residual connection in our residual approximator significantly enhances BR mod els’ ability to generate high-quality item-level bundle embed dings. Experiments on six BRmodelsandfourpublicdatasets from different domains show that RDiffBR improves the per formance of Recall and NDCG of backbone BR models by up to 23%, while only increases training time about 4%.

In the field of Artificial Intelligence (AI), the data used to train models may contain private information that could potentially be exposed in the model’s output. Machine Unlearning (MU) has emerged as a promising solution for removing private or obsolete data from trained models, along with their influence, thereby enforcing the “right to be forgotten” under the General Data Protection Regulation (GDPR). However, achieving a balance between privacy guarantee and model performance remains a fundamental challenge. This paper contributes to the field of AI by presenting an empirical evaluation of key families, i.e., data deletion, data perturbation, and model update of MU for privacy preservation, focusing on their impact on both classification accuracy and privacy in deep learning (DL) models. The study assesses changes in the classification performance of the convolutional neural network (CNN) architecture and the long short-term memory (LSTM) and bidirectional LSTM (Bi-LSTM) recurrent neural network (RNN) architectures when used with data deletion, data perturbation, and model update families of MU. This study also assesses these architectures’ susceptibility to membership inference attacks (MIA) before and after unlearning on PPG-DaLiA and MHEALTH (Mobile HEALTH) datasets, providing a quantitative measure of privacy leakage. Experimental results show that model update techniques offer more scalable alternatives to data deletion and perturbation, though they introduce varying levels of privacy leakage risk. In doing so, this research highlights the strengths and limitations of current targeted unlearning methods and underscores the need for more efficient and flexible approaches to privacy protection in DL models.

ABSTRACT The self‐organisation map is an unsupervised learning technique that discovers patterns and relationships in data without requiring labelled training data. Inspired by the self‐organisation map, Self‐Organised Granular encoding has been shown to be effective for generating reliable discrete data clustering results as it is a data encoding technique that uses fuzzy sets and granularity to handle uncertain and imprecise information within discrete data. However, it is mainly useful for unsupervised learning, and its feasibility for supervised learning has not yet been studied. Also, discrete data classification is still under‐researched. This paper proposes a new discrete data classification method called Transposed Fuzzy Class Granular classification. This method aims to transform discrete data into fuzzy partitions by considering all available classes and generating representations of the trained class's Transposed Fuzzy Class Granular distribution by measuring the total divergence from the average of each fuzzy class's membership degree distribution. The paper introduces a novel approach to discrete data classification by adapting class granules for classification and improving performance by tackling uncertainty, ambiguity, and the unique characteristics of discrete datasets. The study examined seven discrete datasets and compared their performance with eight commonly used classifiers as the baseline. These datasets were naturally discrete or created by discrete partitions of real datasets. The experimental results demonstrate that the proposed classifier outperforms the baseline classifiers in discrete data classification.

An accurate Depth of Anaesthesia (DoA) assessment is crucial for enhancing a patient’s surgical experience, as it helps avoid intraoperative (anaesthesia) awareness and reduces postoperative recovery time and cognitive dysfunction. This article presents two novel research outcomes. The first is the development of a new DoA index using processed Electroencephalogram (EEG) signals and machine learning techniques. This research uniquely combines powerful features extracted by two distinct time series decomposition methods: the Fast Fourier Transform (FFT) and Variation Mode Decomposition (VMD). Permutation Entropy, Multiscale (Permutation) Lempel–Ziv Complexity, Hjorth’s mobility and Petrosian Fractal Dimension features trained a Support Vector Regressor producing a highly responsive DoA index of 85.8% accuracy. Secondly, a novel fixed-period Loss of Consciousness (LoC) early warning system is developed. Using the same feature set, a KNeighbors (KNN) classifier achieves an accuracy and Area Under the Receiver Operating Characteristic Curve of 82% after Synthetic Minority Oversampling Technique (SMOTE) dataset imbalance correction. The KNN model outperforms Decision Trees, Random Forests and Support Vector classification. Reliably predicting the LoC within a fixed period would greatly assist medical practitioners by ensuring an appropriate level of anaesthetic is administered to achieve the LoC, thus reducing the risk of anaesthesia awareness and preventing anaesthetic overdose.

With the continuous growth in the number of parameters of the Transformer-based pretrained language models (PLMs), particularly the emergence of large language models (LLMs) with billions of parameters, many natural language processing (NLP) tasks have demonstrated remarkable success. However, the enormous size and computational demands of these models pose significant challenges for adapting them to specific downstream tasks, especially in environments with limited computational resources. Parameter-Efficient Fine-Tuning (PEFT) offers an effective solution by reducing the number of fine-tuning parameters and memory usage while achieving comparable performance to full fine-tuning. The demands for fine-tuning PLMs, especially LLMs, have led to a surge in the development of PEFT methods, as depicted in Fig. 1. In this paper, we present a comprehensive and systematic review of PEFT methods for PLMs. We summarize these PEFT methods, discuss their applications, and outline future directions. Furthermore, extensive experiments are conducted using several representative PEFT methods to better understand their effectiveness in parameter efficiency and memory efficiency. By offering insights into the latest advancements and practical applications, this survey serves as an invaluable resource for researchers and practitioners seeking to navigate the challenges and opportunities presented by PEFT in the context of PLMs.

Federated Learning (FL) offers a privacy-preserving framework for training audio classification (AC) models across decentralized clients without sharing raw data. However, Federated Audio Classification faces three major challenges: data heterogeneity , model heterogeneity , and data corruption , which degrade performance in real-world settings. While existing methods often address these issues separately, a unified solution remains underexplored. We propose FedMLAC, a mutual learning-based FL framework that tackles all three challenges simultaneously. Each client maintains a personalized local AC model and a lightweight, globally shared Plug-in model. These models interact via bidirectional knowledge distillation, enabling global knowledge sharing while adapting to local data distributions, thus addressing both data and model heterogeneity. To counter data corruption, we introduce a Layer-wise Pruning Aggregation (LPA) strategy that filters anomalous Plug-in updates based on parameter deviations during aggregation. Extensive experiments on four diverse AC benchmarks, including both speech and non-speech tasks, show that FedMLAC consistently outperforms state-of-the-art baselines in classification accuracy and robustness to noisy data.

Cold-start bundle recommendation focuses on modeling new bundles with insufficient information to provide recommendations. Advanced bundle recommendation models usually learn bundle representations from multiple views (e.g., user-bundle interaction views) at both bundle and item levels. Consequently, the cold-start problem for bundles is more challenging than that for traditional items due to the dual-level multi-view complexity. For cold-start bundle recommendation, we propose a novel Mixture of Diffusion Experts (MoDiffE) framework, which employs a divide-and-conquer strategy and consists of three parts: (1) Division : The bundle cold-start problem is divided into view-specific but unified sub-problems: the poor representation of feature-missing bundles in prior-embedding models. (2) Conquest : Diffusion models uniformly solve all sub-problems by directly generating diffusion representations without depending on specific features. (3) Combination : A cold-aware hierarchical Mixture of Experts (MoE) is employed to adaptively combine results of the sub-problems into final recommendations. Additionally, MoDiffE proposes a cold-start gating augmentation method to enable gating for cold bundles. In experiments on three real-world datasets, MoDiffE significantly outperforms existing solutions in cold-start bundle recommendation. It achieves up to a 0.1027 Recall@20 improvement in cold-start scenarios and up to a 47.43% relative improvement in all-bundle scenarios.

In the realm of collaborative filtering recommendation systems, Graph Neural Networks (GNNs) have demonstrated remarkable performance but face significant challenges in deployment on resource-constrained edge devices due to their high embedding parameter requirements and computational costs. Using common quantization method directly on node embeddings may overlooks their graph based structure, causing error accumulation during message passing and degrading the quality of quantized embeddings.To address this, we propose Graph based Node-Aware Dynamic Quantization training for collaborative filtering (GNAQ), a novel quantization approach that leverages graph structural information to enhance the balance between efficiency and accuracy of GNNs for Top-K recommendation. GNAQ introduces a node-aware dynamic quantization strategy that adapts quantization scales to individual node embeddings by incorporating graph interaction relationships. Specifically, it initializes quantization intervals based on node-wise feature distributions and dynamically refines them through message passing in GNN layers. This approach mitigates information loss caused by fixed quantization scales and captures hierarchical semantic features in user-item interaction graphs. Additionally, GNAQ employs graph relation-aware gradient estimation to replace traditional straight-through estimators, ensuring more accurate gradient propagation during training. Extensive experiments on four real-world datasets demonstrate that GNAQ outperforms state-of-the-art quantization methods, including BiGeaR and N2UQ, by achieving average improvement in 27.8% Recall@10 and 17.6% NDCG@10 under 2-bit quantization. In particular, GNAQ is capable of maintaining the performance of full-precision models while reducing their model sizes by 8 to 12 times; in addition, the training time is twice as fast compared to quantization baseline methods.

Knowledge Graphs (KGs) have revolutionized structured knowledge representation, yet their capacity to model real-world complexity and heterogeneity remains fundamentally constrained. The emerging paradigm of Multi-View Knowledge Graphs (MVKGs) addresses this gap through multi-view learning, but existing research lacks systematic integration. This survey provides the first systematic consolidation of MVKG methodologies, with four pivotal contributions: 1) The first unified taxonomy of view generation paradigms that rigorously categorizes view into four types: structure, semantic, representation, and knowledge & modality; 2) A novel methodological typology for view fusion that systematically classifies techniques by fusion targets (feature, decision, and hybrid); 3) Task-centric application mapping that bridges theoretical MVKG constructs to node/link/graph-level downstream tasks; 4) A forward-looking roadmap identifying underexplored challenges. By unifying fragmented methodologies and formalizing MVKG design principles, this survey serves as a roadmap for advancing KG versatility in complex AI-driven scenarios. In doing so, it paves the way for more efficient knowledge integration, enhanced decision-making, and cross-domain learning in real-world applications.

One-Shot Federated Learning (OSFL) restricts communication between the server and clients to a single round, significantly reducing communication costs and minimizing privacy leakage risks compared to traditional Federated Learning (FL), which requires multiple rounds of communication. However, existing OSFL frameworks remain vulnerable to distributional heterogeneity, as they primarily focus on model heterogeneity while neglecting data heterogeneity. To bridge this gap, we propose FedHydra, a unified, data-free, OSFL framework designed to effectively address both model and data heterogeneity. Unlike existing OSFL approaches, FedHydra introduces a novel two-stage learning mechanism. Specifically, it incorporates model stratification and heterogeneity-aware stratified aggregation to mitigate the challenges posed by both model and data heterogeneity. By this design, the data and model heterogeneity issues are simultaneously monitored from different aspects during learning. Consequently, FedHydra can effectively mitigate both issues by minimizing their inherent conflicts. We compared FedHydra with five SOTA baselines on four benchmark datasets. Experimental results show that our method outperforms the previous OSFL methods in both homogeneous and heterogeneous settings. The code is available at https://github.com/Jun-B0518/FedHydra.

With the rise of generative models, video-language cross-modal applications have seen significant growth. Generating procedural text from instructional videos has become a crucial task, playing a key role in both understanding visual scenes and supporting practical applications. The sequential nature of video clips is particularly important, as entities may appear across multiple clips, reflecting fine-grained intra-modal self-similarity. However, most existing training methods treat other clips in a sequence as negative samples when a target is specified, neglecting their step-wise correlations. To address this limitation, we introduce Step-wise Soft Alignment via OpTimal TrAnsport (SATA), which constructs soft positive pairs to mitigate the issue. SATA first generates a step-wise similarity matrix by leveraging visual representations and generated procedural text. It then aligns the step-wise distributions between procedural text and video clips using optimal transport. The resulting transport distance serves as a weight, treating these pairs as soft positives for contrastive learning, ultimately improving the accuracy of procedural text generation. Our experiments on the publicly available YouCookII and ActivityNet Captions datasets demonstrate the effectiveness of SATA, achieving absolute improvements of 0.5% to 1.7% and 0.6% to 14.9% in paragraph-level evaluation, respectively.

Shaopeng Tang, Lin Li, Xiaohui Tao, Leqi Zhong, Qing Xie. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

The imperative of user privacy protection and regulatory compliance necessitates sensitive data removal in model training, yet this process often induces distributional shifts that undermine model performance-particularly in out-of-distribution (OOD) scenarios. We propose a novel data removal approach that enhances deep predictive models through factor decorrelation and loss perturbation. Our approach introduces: (1) a discriminative-preserving factor decorrelation module employing dynamic adaptive weight adjustment and iterative representation updating to reduce feature redundancy and minimize inter-feature correlations. (2) a smoothed data removal mechanism with loss perturbation that creates information-theoretic safeguards against data leakage during removal operations. Extensive experiments on five benchmark datasets show that our approach outperforms other baselines and consistently achieves high predictive accuracy and robustness even under significant distribution shifts. The results highlight its superior efficiency and adaptability in both in-distribution and out-of-distribution scenarios.

The application of metric learning in recommender systems has gained considerable attention, particularly for enabling supervised training through Euclidean distance. However, conventional collaborative translational metric learning typically represents each user and item as a single point and projects collaborative signals onto a specific translation vector within a uniform space. This approach fails to explicitly capture the high-order semantics and dynamic nature of user-item interactions derived from implicit user behavior. Given the extensive research on graph neural networks (GNNs), a natural extension is to incorporate high-order information into the generation of translation vectors. Yet, our empirical findings reveal that the performance is not as expected. In this paper, we systematically investigate the limitations of existing methods and attribute the issue to semantic confusion. Motivated by this finding, we propose a novel framework that integrates bilateral metric learning with a causal graph network. Specifically, we construct a structural causal model (SCM) to disentangle user behavior into causal features and confounders. To mitigate the influence of these confounders, we propose a conditional intervention module that generates confounder-specific conditions for the target. Moreover, inspired by this conditional intervention mechanism, we develop an additional module conditioned on user behavior to enhance the diversity of the recommended list, recognizing that diversity is also a crucial metric for evaluating recommendation quality. We conducted a series of experiments to validate the effectiveness of our proposed method. The results demonstrate that our approach achieves state-of-the-art performance in terms of both recommendation accuracy and diversity.

Classifying graph-structured data presents significant challenges due to the diverse features of nodes and edges and their complex relationships. While Graph Neural Networks (GNNs) are widely used for graph prediction tasks, their performance is often hindered by these intricate dependencies. Leveraging causality holds potential in overcoming these challenges by identifying causal links among features, thus enhancing GNN classification performance. However, depending solely on adjacency matrices or attention mechanisms, as commonly studied in causal prediction research, is insufficient for capturing the complex interactions among features. To address these challenges, we present HebCGNN , a Hebbian-enabled Causal GNN classification model that incorporates dynamic impact valuing . Our method creates a robust framework that prioritizes causal elements in prediction tasks. Extensive experiments on seven publicly available datasets across diverse domains demonstrate that HebCGNN outperforms state-of-the-art models.

Reinforcement learning has been increasingly applied in monitoring applications because of its ability to learn from previous experiences and make adaptive decisions. However, existing machine learning-based health monitoring applications are mostly supervised learning algorithms, trained on labels, and they cannot make adaptive decisions in an uncertain, complex environment. This study proposes a novel and generic system, predictive deep reinforcement learning (PDRL), with multiple RL agents in a time series forecasting environment. The proposed generic framework accommodates virtual Deep Q Network (DQN) agents to monitor predicted future states of a complex environment with a well-defined reward policy so that the agent learns existing knowledge while maximizing their rewards. In the evaluation process of the proposed framework, three DRL agents were deployed to monitor a subject’s future heart rate, respiration, and temperature predicted using a BiLSTM model. With each iteration, the three agents were able to learn the associated patterns, and their cumulative rewards gradually increased. It outperformed the baseline models for all three monitoring agents. The proposed PDRL framework achieves state-of-the-art performance in time series forecasting by effectively integrating reinforcement learning agents with deep learning-based prediction. The proposed DRL agents and deep learning model in the PDRL framework are customized to enable transfer learning in other forecasting applications like traffic and weather, and monitor their states. The PDRL framework is able to learn the future states of the traffic and weather forecasting, and the cumulative rewards are gradually increasing over each episode.

A knowledge graph (KG) is a form of representing knowledge of the objective world. With the expansion of knowledge, KGs frequently incorporate new entities, which often possess limited associated data, known as few-shot features. Addressing the missing knowledge for these emerging entities is crucial practically, but there are significant challenges due to data scarcity. Previously developed methods based on knowledge graph embedding (KGE) and graph neural networks (GNNs) focusing on instance-level KGs are confronted with challenges of data scarcity and model simplicity, rendering them inapplicable to reasoning tasks in few-shot scenarios. To tackle these issues, we propose a multi-view few-shot KG reasoning method for emerging entities. The primary focus of our method lies in resolving the problem of link prediction for emerging entities with limited associated triples from multiple perspectives. Distinct from previous methods, our approach initially abstracts a concept-view KG from the conventional instance-view KG, enabling the formulation of commonsense rules. Additionally, we employ the aggregation of multi-hop subgraph features to enhance the representation of emerging entities. Furthermore, we introduce a more efficient cross-domain negative sampling strategy and a multi-view triple scoring function based on commonsense rules. Our experimental evaluations highlight the effectiveness of our method in few-shot contexts, demonstrating its robustness and adaptability in both cross-shot and zero-shot scenarios, significantly outperforming existing models in these challenging settings.

Happiness prediction based on large-scale online data and machine learning models is an emerging research topic that underpins a range of issues, from personal growth to social stability. Many advanced machine learning (ML) models with explanations are used for happiness online assessment while maintaining high accuracy of results. However, expert feedback and sociological theory may be absent from these models, which limits the association between prediction results and the right reasons for why they occurred. Sociological studies have shown that primary and secondary relations are inherent in happiness factors, which can be used as domain knowledge to guide model training. Inspired by such insights, this article attempts to provide new insights into the explanation consistency from an empirical study perspective. Then this article studies how to represent and introduce domain knowledge constraints to make ML models more trustworthy. We achieve this by 1) proving that multiple prediction models with additive factor attributions will have the desirable property of primary and secondary relations consistency; and 2) showing that factor relations with quantity can be represented as an importance distribution for encoding domain knowledge. Factor explanation difference is penalized by the Wasserstein distance among prediction models. Experimental results using two online datasets show that domain knowledge of stable factor relations exists. Using this knowledge not only improves happiness prediction accuracy but also reveals more significant happiness factors for assisting decisions.

Machine unlearning (MU) is gaining increasing attention due to the need to remove or modify predictions made by machine learning (ML) models. While training models have become more efficient and accurate, the importance of unlearning previously learned information has become increasingly significant in fields such as privacy, security, and ethics. This article presents a comprehensive survey of MU, covering current state-of-the-art techniques and approaches, including data deletion, perturbation, and model updates. In addition, commonly used metrics and datasets are presented. This article also highlights the challenges that need to be addressed, including attack sophistication, standardization, transferability, interpretability, training data, and resource constraints. The contributions of this article include discussions about the potential benefits of MU and its future directions. Additionally, this article emphasizes the need for researchers and practitioners to continue exploring and refining unlearning techniques to ensure that ML models can adapt to changing circumstances while maintaining user trust. The importance of unlearning is further highlighted in making artificial intelligence (AI) more trustworthy and transparent, especially with the growing importance of AI across various domains that involve large amounts of personal user data.

Abstract The expansion of Graph Neural Networks (GNNs) has highlighted the importance of evaluating their performance in real-world scenarios. However, existing evaluation frameworks often overlook the integration of causality, a critical component that is essential for more robust evaluation of GNNs. To address this gap, we present a benchmark study that systematically compares standard and causal GNN models with a focus on classification tasks. Our analysis encompasses a careful selection of nine GNN models across seven diverse datasets that span three distinct domains. The results reveal the following: I) Causality-enhanced GNNs consistently outperform their traditional counterparts in graph classification tasks; II) Models integrating causal features exhibit greater generalizability across varied datasets; and III) Incorporation of causal elements significantly improves the predictive accuracy of GNNs. These findings highlight the importance of embedding causality in the evaluation and development of GNNs for improved performance and application.

Urban air quality prediction models can predict pollutant values based on its time series. Existing research shows that the correlation between influencing factors is dynamic. In this paper, we propose an Urban Air Quality Prediction Model based on Dynamic Correlation of Influencing Factors (DynamicAir) to address this problem. In the dynamic correlation module, the dynamic correlation of influencing factors is captured by dynamic graph generation and dynamic graph convolution; in the multi-time-step prediction module, the time correlation of each step and the dynamic correlation of influencing factors are mapped by multi-layer non-linear mapping to obtain the future pollutant concentration values at multi-steps. Experimental results on two real datasets(Beijing Capital International Airport and Beijing Olympic Sports Centre) show that the proposed DynamicAir reduces the RMSE by 1.15% and 4.04% respectively compared to the state-of-the-art baseline model (with a statistical interval of three hours).

Personality analysis can help individuals gain self-awareness, improve decision-making skills, and enhance relationships, while also providing valuable insights in fields like psychology, human resources, and marketing. Computational models, including traditional machine learning and deep learning models, have been beneficial in analyzing the impact of personality in sociological studies, especially deep learning models with interpretability. However, different computational models may produce different explanation results, which poses a challenge for social studies researchers in selecting appropriate explanations, as each model provides distinct prediction accuarcy values and explanation. To this end, this work introduces a computational personality analysis framework that incorporates Local Interpretable Model-Agnostic Explanations (LIME) to investigate analysis methods. The framework covers various computational personality models, encompasses pre-processing techniques, feature embedding, and focuses specifically on Myers-Briggs Type Indicator (MBTI) personality analysis, enabling valuable insights from predictions generated by diverse computational models. Cosine similarity is employed to evaluate the variations in explanation results produced by different computational models in relation to personality analysis. Our experiment reveals the key finding: although they have comparable predictive accuracy, there are not small explanation differences among the computational models.

Meal recommendation, as a typical health-related recommendation task, contains complex relationships between users, courses, and meals. Among them, meal-course affiliation associates user-meal and user-course interactions. However, an extensive literature review demonstrates that there is a lack of publicly available meal recommendation datasets including meal-course affiliation. Meal recommendation research has been constrained in exploring the impact of cooperation between two levels of interaction on personalization and healthiness. To pave the way for meal recommendation research, we introduce a new benchmark dataset called MealRec^+. Due to constraints related to user health privacy and meal scenario characteristics, the collection of data that includes both meal-course affiliation and two levels of interactions is impeded. Therefore, a simulation method is adopted to derive meal-course affiliation and user-meal interaction from the user's dining sessions simulated based on user-course interaction data. Then, two well-known nutritional standards are used to calculate the healthiness scores of meals. Moreover, we experiment with several baseline models, including separate and cooperative interaction learning methods. Our experiment demonstrates that cooperating the two levels of interaction in appropriate ways is beneficial for meal recommendations. The dataset is available on GitHub (https://github.com/WUT-IDEA/MealRecPlus).

Abstract The introduction of blockchain technology has brought about significant transformation in the realm of digital transactions, providing a secure and transparent platform for peer-to-peer interactions that cannot be tampered with. The decentralised and distributed nature of blockchains guarantees the integrity and authenticity of the data, eliminating the need for intermediaries. The applications of this technology are not limited to the financial sector, but extend to various areas, such as supply chain management, identity verification, and governance. At the core of these blockchains is the consensus mechanism, which plays a crucial role in ensuring the reliability and integrity of a system. Consensus mechanisms are essential for achieving an agreement amongst network participants regarding the validity of transactions and the order in which they are recorded on the blockchain. By incorporating consensus mechanisms, blockchains ensure that all honest nodes in the network reach a consensus on whether to accept or reject a block, based on predefined rules and criteria. The aim of this study is to introduce a novel consensus mechanism named Erdos, which seeks to address the shortcomings of existing consensus algorithms, such as the Proof of Work and Proof of Stake. Erdos emphasises security, decentralisation, and fairness. One notable feature of this mechanism is its equitable node-selection algorithm, which ensures equal opportunities for all nodes to engage in block creation and validation. In addition, Erdos implements a deterministic block finalisation process that guarantees the integrity and authenticity of the blockchain. The main contribution of this research lies in its innovative approach to deterministic block finalisation, which effectively mitigates the various security risks associated with blockchain systems.

Federated Learning (FL) is currently one of the most popular technologies in the field of Artificial Intelligence (AI) due to its collaborative learning and ability to preserve client privacy. However, it faces challenges such as non-identically and non-independently distributed (non-IID) data with imbalanced labels among local clients. To address these limitations, the research community has explored various approaches such as using local model parameters, federated generative adversarial learning, and federated representation learning. In our study, we propose a novel Clustered FedStack framework based on the previously published Stacked Federated Learning (FedStack) framework. Here, the local clients send their model predictions and output layer weights to a server, which then builds a robust global model. This global model clusters the local clients based on their output layer weights using a clustering mechanism. We adopt three clustering mechanisms, namely K-Means, Agglomerative, and Gaussian Mixture Models, into the framework and evaluate their performance. Bayesian Information Criterion (BIC) is used with the maximum likelihood function to determine the number of clusters. Our results show that Clustered FedStack models outperform baseline models with clustering mechanisms. To estimate the convergence of our proposed framework, we use Cyclical learning rates.

Sequential Crime Prediction (SCP) aims to analyze future criminal intents within historical event transitions and predict next crime event. A problem lies in the correlations among different event features (e.g., time, locations, and categories), posing challenges to capture a comprehensive criminal intent. Most existing methods are hard to fully exploit event descriptions and locations in raw crime records to model such correlations. To this end, this paper proposes a Semantics and Geography aware hierarchical learning framework (SaGCrime). First, we employ BERT to encode semantic representations from descriptions and a proposed geography encoder to learn geographical representations from exact GPS-based locations, respectively. Then, these representations are fed into a stacked Transformer encoder to learn multi-modal interactive intent representation of next crime event. Experiments on real-world crime datasets show that our SaGCrime achieves relatively 4.70% and 3.64% improvements in terms of NDCG@5, compared with state-of-the-art methods.

Personalized clinical decision support systems are increasingly being adopted due to the emergence of data-driven technologies, with this approach now gaining recognition in critical care. The task of incorporating diverse patient conditions and treatment procedures into critical care decision-making can be challenging due to the heterogeneous nature of medical data. Advances in Artificial Intelligence (AI), particularly Reinforcement Learning (RL) techniques, enables the development of personalized treatment strategies for severe illnesses by using a learning agent to recommend optimal policies. In this study, we propose a Deep Reinforcement Learning (DRL) model with a tailored reward function and an LSTM-GRU-derived state representation to formulate optimal treatment policies for vasopressor administration in stabilizing patient physiological states in critical care settings. Using an ICU dataset and the Medical Information Mart for Intensive Care (MIMIC-III) dataset, we focus on patients with Acute Respiratory Distress Syndrome (ARDS) that has led to Sepsis, to derive optimal policies that can prioritize patient recovery over patient survival. Both the DDQN ( RepDRL-DDQN ) and Dueling DDQN ( RepDRL-DDDQN ) versions of the DRL model surpass the baseline performance, with the proposed model’s learning agent achieving an optimal learning process across our performance measuring schemes. The robust state representation served as the foundation for enhancing the model’s performance, ultimately providing an optimal treatment policy focused on rapid patient recovery.

Food computing, a newly emerging topic, is closely linked to human life through computational methodologies. Meal recommendation, a food-related study about human health, aims to provide users a meal with courses constrained from specific categories (e.g., appetizers, main dishes) that can be enjoyed as a service. Historical interaction data, important user information, is often used by existing models to learn user preferences. However, if a user’s preferences favor less healthy meals, the model will follow that preference and make similar recommendations, potentially negatively impacting the user’s long-term health. This emphasizes the necessity for health-oriented and responsible meal recommendation systems. In this article, we propose a healthiness-aware and category-wise meal recommendation model called CateRec, which boosts healthiness exposure by using nutritional standards as knowledge to guide the model training. Two fundamental questions are raised and answered: (1) How can the healthiness of meals be evaluated? Two well-known nutritional standards from the World Health Organization and the United Kingdom Food Standards Agency are used to calculate the healthiness score of the meal. (2) How can the model training be guided in a health-oriented manner? We construct category-wise personalization partial rankings and category-wise healthiness partial rankings, and theoretically analyze that they meet the necessary properties and assumptions required to be trained by the maximum posterior estimator under Bayesian probability. The data analysis confirms the existence of user preferences leaning towards less healthy meals in two public datasets. A comprehensive experiment demonstrates that our CateRec effectively boosts healthiness exposure in terms of mean healthiness score and ranking exposure while being comparable to the state-of-the-art model in terms of recommendation accuracy.

Machine Unlearning, a pivotal field addressing data privacy in machine learning, necessitates efficient methods for the removal of private or irrelevant data. In this context, significant challenges arise, particularly in maintaining privacy and ensuring model efficiency when managing outdated, private, and irrelevant data. Such data not only compromises model accuracy but also burdens computational efficiency in both learning and unlearning processes. To mitigate these challenges, we introduce a novel framework: Attention-based Machine Unlearning using Federated Reinforcement Learning (FRAMU). This framework incorporates adaptive learning mechanisms, privacy preservation techniques, and optimization strategies, making it a well-rounded solution for handling various data sources, either single-modality or multi-modality, while maintaining accuracy and privacy. FRAMU's strengths include its adaptability in fluctuating data landscapes, its ability to unlearn outdated, private, or irrelevant data, and its support for continual model evolution without compromising privacy. Our experiments, conducted on both single-modality and multi-modality datasets, revealed that FRAMU significantly outperformed baseline models. Additional assessments of convergence behavior and optimization strategies further validate the framework's utility in federated learning applications. Overall, FRAMU advances Machine Unlearning by offering a robust, privacy-preserving solution that optimizes model performance while also addressing key challenges in dynamic data environments.

Sequential prediction has great value for resource allocation due to its capability in analyzing intents for next prediction. A fundamental challenge arises from real-world interaction dynamics where similar sequences involving multiple intents may exhibit different next items. More importantly, the character of volume candidate items in sequential prediction may amplify such dynamics, making deep networks hard to capture comprehensive intents. This article presents a sequential prediction framework with Decoupled Progressive Distillation (DePoD), drawing on the progressive nature of human cognition. We redefine target and non-target item distillation according to their different effects in the decoupled formulation. This can be achieved through two aspects: (1) Regarding how to learn, our target item distillation with progressive difficulty increases the contribution of low-confidence samples in the later training phase while keeping high-confidence samples in the earlier phase. And, the non-target item distillation starts from a small subset of non-target items from which size increases according to the item frequency. (2) Regarding whom to learn from, a difference evaluator is utilized to progressively select an expert that provides informative knowledge among items from the cohort of peers. Extensive experiments on four public datasets show DePoD outperforms state-of-the-art methods in terms of accuracy-based metrics.

Recommender Systems are mainly used in various e-commerce applications, especially online stores threatening users’ privacy. The privacy issues can be overcome by using security solutions, which include blockchain technology for privacy applications. The fusion of the Internet of Things and blockchain technology has fully improved modern distributed systems. The combination guarantees the safety and scalability of the recommender system. We aim to create an authorized secure exchange device using blockchain-enabled multiparty computation by adding smart contracts to the core blockchain protocol. The recommendation structure and Blockchain technology make online shopping more convenient and private. We propose a blockchain-related recommender system using the “movielens” data. The case study includes a smart contract model that recommends movies to buyers. Initially, we tested the model on a small “movielens dataset” and extended it to a 3M movielens dataset. We developed a classifier model for movielens and proposed a Dual light graph convolutional network for movielens data classification. Our results, including ablation analysis, show that blockchain strategies and Dual light graph convolutional networks can effectively improve recommender systems’ privacy. Furthermore, the suggested blockchain technique can be stretched by similar procedures.

Current sentence-level evidence extraction based methods may lose the discourse coherence of legal articles since they tend to make the extracted sentences scattered over the article. To solve the problem, this paper proposes a Cascaded Answer-guided key segment learning framework for long Legal article Question Answering, namely CALQA. The framework consists of three cascaded modules: Sifter, Reader, and Responder. The Sifter transfers a long legal article into several segments and works in an answer-guided way by automatically sifting out key fact segments in a coarse-to-fine approach through multiple iterations. The Reader utilizes a set of attention mechanisms to obtain semantic representations of the question and key fact segments. Finally, considering it a multi-label classification task the Responder predicts final answers in a cascaded manner. CALQA outperforms state-of-the-art methods in CAIL 2021 Law dataset.

Bundle recommendation suggests a set of items to users against their complex needs, where user-bundle interaction learning is key. It is observed that Gromov’s δ-hyperbolicity of the interaction graph in bundle recommendation is smaller (lower is more hyperbolic) than those in traditional item recommendation when measuring a graph’s tree likeness. However, state-of-the-art bundle recommendation methods learn to embed the entities (user, bundle, item) of tree-like interaction graph in Euclidean space, which could cause severe distortion problems. We argue hyperbolic space provides a promising way to get accurate entity embeddings, with this paper proposing a novel bundle recommendation model. The model learns user preferences via hyperbolic graph convolution, aiming at decreasing the distortion of bundle graph node embeddings. Extensive empirical experiments conducted on two real-world datasets confirm that our model achieves promising performance compared to baseline methods representing state-of-the-art bundle recommendation methods.

Memes are one of the most popular social media in online disinformation campaigns. Their creators often use a variety of rhetoric and psychological skills to achieve the purpose of misinformed audiences. These characteristics lead to the unsatisfactory performance of memes category detection tasks, such as predicting propaganda techniques, being harmful or not, and so on. To this end, we propose a novel memes category detection model via Be-or-Not Prompt Enhanced hard Negatives generating (BNPEN). Firstly, our BNPEN is reformulated into a contrastive learning-based image-text matching (ITM) task through category-padded prompt engineering. Secondly, we design the be-or-not prompt templates to keep the writing style of memes and create hard negative image-text pairs. Finally, our negatives generating can alleviate the negative-positive-coupling (NPC) effects in contrastive learning, thus improving the image-text matching quality. Conducted on two public datasets, experimental results show that our BNPEN is better than the off-the-shelf multi-modal learning models in terms of F1 and Accuracy measures.

Researchers have been aware that emotion is not one-hot encoded in emotion-relevant classification tasks, and multiple emotions can coexist in a given sentence. Recently, several works have focused on leveraging a distribution label or a grayscale label of emotions in the classification model, which can enhance the one-hot label with additional information, such as the intensity of other emotions and the correlation between emotions. Such an approach has been proven effective in alleviating the overfitting problem and improving the model robustness by introducing a distribution learning component in the objective function. However, the effect of distribution learning cannot be fully unfolded as it can reduce the model’s discriminative ability within similar emotion categories. For example, “Sad” and “Fear” are both negative emotions. To address such a problem, we proposed a novel emotion extension scheme in the prior work (Li, Chen, Xie, Li, and Tao, 2021). The prior work incorporated fine-grained emotion concepts to build an extended label space, where a mapping function between coarse-grained emotion categories and fine-grained emotion concepts was identified. For example, sentences labeled “Joy” can convey various emotions such as enjoy, free, and leisure. The model can further benefit from the extended space by extracting dependency within fine-grained emotions when yielding predictions in the original label space. The prior work has shown that it is more apt to apply distribution learning in the extended label space than in the original space. A novel sparse connection method, i.e., Leaky Dropout, is proposed in this paper to refine the dependency-extraction step, which further improves the classification performance. In addition to the multiclass emotion classification task, we extensively experimented on sentiment analysis and multilabel emotion prediction tasks to investigate the effectiveness and generality of the label extension schema.

Blockchain-enabled smart contracts have revolutionized the insurance industry due to their potential to streamline backend operations, mitigate fraudulent claims, and enhance data security and transparency. Guided by the design science methodology, the authors propose two specific smart contract frameworks to enhance insurance claims processing related to vehicle damage claims and personal injury claims. These proposed frameworks can improve the overall efficiency and effectiveness of insurance claims processing by automating claims submission, review, analysis, and payment, while reducing fraud and data leakage, by merging various data sources and disintermediation. Furthermore, the authors design a smart contract template supported by eight operational algorithms to facilitate the processing of insurance claims with the help of smart contracts. This template provides practitioners with a standardized prototype for the development of secure and efficient insurance applications.

The convergence of systems neuroscience and open science arouses great interest in the current brain big data era, highlighting the thinking capability of intelligent agents in handling multi-source knowledge, information and data across various levels of granularity. To realize such thinking-inspired brain computing during a brain investigation process, one of the major challenges is to find a holistic brain map that can model multi-dimensional variables of brain investigations across brain functions, experimental tasks, brain data and analytical methods synthetically. In this paper, we propose a context-enhanced graph learning method to fuse open knowledge from different sources, including: contextual information enrichment, structural knowledge fusion, and holistic graph learning. Such a method can enhance contextual learning of abstract concepts and relational learning between two concepts that have large gap from different dimensions. As a result, an extensible space, namely Thinking Space, is generated to represent holistic variables and their relations in a map, which currently contributes to the field of brain research for systematic brain computing. In the future, the Thinking Space coupled with the rapid development and spread of artificial intelligence generated content will be developed in more scenarios so as to promote global interactions of intelligence in the connected world.

The analysis of electroencephalogram (EEG) signals can provide valuable insights to the nature of many diseases such as Alzheimer, epilepsy, sleep problems and thus can improve our understating and treatment about them. One of the major EEG signal applications is related to Epilepsy. The main contribution of this work is the proposal of an effective scheme for classifying the EEG signals for the study of epilepsy based on Fast Fourier Transform (FFT) under an ensemble model. The EEG signals are decomposed into frequency bands by using Fast Fourier Transform to extract the key statistical features, which are then fed into an ensemble model to classify the epileptic patients. Three base classifiers – Naïve Bayes, Least Square Support Vector Machine and Neural Networks - are utilized to construct the ensemble framework. The final decision of classification is dependent on the aggregation of the three classifiers decisions. The experimental results demonstrated that the proposed technique is a promising tool in accurately classifying the epileptic EEG signals.

Evaluating the high-effect factors of citizens' happiness is beneficial to a wide range of policy-making for economics and politics in most countries. Benefiting from the high-efficiency of regression models, previous efforts by sociology scholars have analyzed the effect of happiness factors with high interpretability. However, restricted to their research concerns, they are specifically interested in some subset of factors modeled as linear functions. Recently, deep learning shows promising prediction accuracy while addressing challenges in interpretability. To this end, we introduce Shapley value that is inherent in solid theory for factor contribution interpretability to work with deep learning models by taking into account interactions between multiple factors. The proposed solution computes the Shapley value of a factor, i.e., its average contribution to the prediction in different coalitions based on coalitional game theory. Aiming to evaluate the interpretability quality of our solution, experiments are conducted on a Chinese General Social Survey (CGSS) questionnaire dataset. Through systematic reviews, the experimental results of Shapley value are highly consistent with academic studies in social science, which implies our solution for citizens' happiness prediction has 2-fold implications, theoretically and practically.

Recent advances in remote patient monitoring (RPM) systems can recognize various human activities to measure vital signs, including subtle motions from superficial vessels. There is a growing interest in applying artificial intelligence (AI) to this area of healthcare by addressing known limitations and challenges such as predicting and classifying vital signs and physical movements, which are considered crucial tasks. Federated learning is a relatively new AI technique designed to enhance data privacy by decentralizing traditional machine learning modeling. However, traditional federated learning requires identical architectural models to be trained across the local clients and global servers. This limits global model architecture due to the lack of local models’ heterogeneity. To overcome this, a novel federated learning architecture, FedStack, which supports ensembling heterogeneous architectural client models was proposed in this study. This work offers a protected privacy system for hospitalized in-patients in a decentralized approach and identifies optimum sensor placement. The proposed architecture was applied to a mobile health sensor benchmark dataset from 10 different subjects to classify 12 routine activities. Three AI models, artificial neural network (ANN), convolutional neural network (CNN), and bidirectional long short-term memory (Bi-LSTM) were trained on individual subject data. The federated learning architecture was applied to these models to build local and global models capable of state-of-the-art performances. The local CNN model outperformed ANN and Bi-LSTM models on each subject data. Our proposed work has demonstrated better performance for heterogeneous stacking of the local models compared to homogeneous stacking. Further analysis of the global heterogeneous CNN model determined that the optimum placement of the sensors on human limbs resulted in better activity recognition. This work sets the stage to build an enhanced RPM system that incorporates client privacy to assist with clinical observations for patients in an acute mental health facility and ultimately help to prevent unexpected death.

Hard interaction learning between source sequences and their next targets is challenging, which exists in a myriad of sequential prediction tasks. During the training process, most existing methods focus on explicitly hard interactions caused by wrong responses. However, a model might conduct correct responses by capturing a subset of learnable patterns, which results in implicitly hard interactions with some unlearned patterns. As such, its generalization performance is weakened. The problem gets more serious in sequential prediction due to the interference of substantial similar candidate targets.

With an innovation to offer in product & services in the Banking and Financial Services Industry, FinTech has received both attention from investors and regulatory bodies across globe. With a primary objective to improve financial inclusion for unbanked population in emerging economies through mobile devices, Fintech have become new commercial entities that promise to deliver millennium goals of World Bank and G20 nations. The availability of huge user data due to use of mobile devices and its use to generate sales of financial products, FinTech companies and solutions are constantly changing and are unique to each Fintech company. Fintech have devised a business model to provide financial services in the form of payment services, wealth management, crowd funding, lending services, forex services for remittance, digital wallets and digital currencies. The data driven business model, connected customers over mobile phones and several financial services demand new regulatory framework that also protects consumers and prevents systemic risk in the economy. In this paper, we have identified the regulatory guidelines issued for various financial product for customers and challenges Fintech will need to solve to provide innovative services. The paper aims to cover the life cycle of products, scope of innovation for Fintech and methods to meet requirements by regulatory bodies. This paper covers the requirements by products in “Account Services” offered by Banking and Financial Services Industry.

Banking and Financial Services Corporations operating on cloud infrastructure is constantly upgrading the application and cloud technologies based on business requirements and new features available. With IaaS and PaaS platforms being managed and upgraded by cloud services providers, the SaaS platform is operated, monitored and governed by bank's technology department. SaaS continues to be the platform under constant upgrade and development considering the need and change in business scenarios. SaaS platform in cloud infrastructure also acts as a channel to enable banking business with new tools and techniques, keeping existing infrastructure capability & scalability within compliance framework. SaaS platform hosts critical applications required for every operations of Bank which includes core banking application, internet banking platform, Card processing applications, ATM & EFTPOS networks and security monitoring tools. Considering the business criticality and application value, SaaS platform is configured to avoid business disruptions. In this paper we have discussed the challenges in deploying the changes required in applications over SaaS platform and methods to mitigate those challenges with minimum or no disruption to cloud architecture infrastructure.

Sentiment analysis classification models trained using neural networks require large amounts of data, but collecting these datasets requires significant time and resources. Although artificial data has been used successfully in computer vision, there are few effective and generalizable methods for creating artificial augmented text data. In this paper, a text based data augmentation method is proposed called back-and-forth translation that can be used to artificially increase the size of any natural language dataset. By creating augmented text data and adding it to the original dataset, it is demonstrated by empirical experiments that back-and-forth translation data augmentation can reduce the error rate in binary sentiment classification models by up to 3.4%. These results are shown to be statistically significant.

Learning based credit prediction has attracted great interest from academia and industry. Different institutions hold a certain amount of credit data with limited users to build model. An institution has the requirement to obtain data from other institutions for improving model performance. However, due to the privacy protection and subject to legal restrictions, they encounter difficulties in data exchange. This affects the performance of credit prediction. In order to solve the above problem, this paper proposes a federated learning based semi-supervised credit prediction approach enhanced by multi-layer label mean, which can aggregate parameters of each institution via joint training while protecting the data privacy of each institution. Moreover, in actual production and life, there are usually more unlabeled credit data than labeled ones, and the distribution of their feature space presents multiple data-dense divisions. To deal with these, local meanNet model is proposed with a multi-layer label mean based semi-supervised deep learning network. In addition, this paper introduces a cost-sensitive loss function in the supervised part of the local mean model. Conducted on two public credit datasets, experimental results show that our proposed federated learning based approach has achieved promising credit prediction performance in terms of Accuracy and F1 measures. At the same time, the framework design mode that splits data aggregation and keys uniformly can improve the security of data privacy and enhance the flexibility of model training.

Abstract Exploiting hand-crafted lexicon knowledge to enhance emotional or sentimental features at word-level has become a widely adopted method in emotion-relevant classification studies. However, few attempts have been made to explore the emotion construction in the classification task, which provides insights to how a sentence’s emotion is constructed. The major challenge of exploring emotion construction is that the current studies assume the dataset labels as relatively independent emotions, which overlooks the connections among different emotions. This work aims to understand the coarse-grained emotion construction and their dependency by incorporating fine-grained emotions from domain knowledge. Incorporating domain knowledge and dimensional sentiment lexicons, our previous work proposes a novel method namedEmoChannelto capture the intensity variation of a particular emotion in time series. We utilize the resultant knowledge of 151 available fine-grained emotions to comprise the representation of sentence-level emotion construction. Furthermore, this work explicitly employs a self-attention module to extract the dependency relationship within all emotions and proposeEmoChannel-SANetwork to enhance emotion classification performance. We conducted experiments to demonstrate that the proposed method produces competitive performances against the state-of-the-art baselines on both multi-class datasets and sentiment analysis datasets.

With the advent of data mining and business processes automation, outlier detection has evolved into a major problem attracting significant research in relation to several application domains. Further advances in Global Positioning system, tracking of anomalous events based on data enhances effective decision making and pro-active measures to overcome risks and avoid unwarranted outputs. Significant work has been done in trajectory outlier detection although no singular approach fits all the domains. By including position and collective outliers on the same visualizations will enhance understanding of an outlier behavior. As such, we have leveraged Hidden Markov Method for prediction-based point outlier detection and pattern mining to identify points or segments of outliers in trajectory data.

Predicting workplace injury using automated techniques opens newer possibilities in evidence-based research. This paper presents our preliminary research in a PhD project in predicting workplace incidents using machine learning algorithms. The analysis on the model performance using several mainstream machine learning algorithms including random forest, k-nearest neighbor and decision tree indicated that the general performance of the decision tree model was found to be statistically higher than that of the other two algorithms.

Deep clustering aims to cluster unlabeled real-world samples by mining deep feature representation. Most of existing methods remain challenging when handling high -dimensional data and simultaneously exploring the complementarity of deep feature representation and clustering. In this paper, we propose a novel Deep Variational Attention Encoder-decoder for Clustering (DVAEC). Our DVAEC improves the representation learning ability by fusing variational attention. Specifically, we design a feature-aware automatic clustering module to mitigate the unreliability of similarity calculation and guide network learning. Besides, to further boost the performance of deep clustering from a global perspective, we define a joint optimization objective to promote feature representation learning and automatic clustering synergistically. Extensive experimental results show the promising performance achieved by our DVAEC on six datasets comparing with several popular baseline clustering methods.

Forecasting the traffic flow is a critical issue for researchers and practitioners in the field of transportation. Using the graph convolutional network (GCN) is widespread in traffic flow forecasting. Existing GCN-based methods mostly rely on undirected spatial correlations to represent the features of spatial-temporal graph. What's more, the traffic flow renders two types of spatial correlations, including the stable correlation constrained by the fixed road structure and the dynamic correlation influenced by the traffic fluctuation. In this paper, we propose a two-stream graph convolutional network by considering stable and dynamic correlations in parallel, which is an end-to-end deep learning framework for dynamic traffic forecasting. We present an auto-decomposing layer to decompose real-time traffic flow data into a stable component and a dynamic component with different spatial correlations. Specifically, the stable component is constrained by the physical road network, and the dynamic component represents fluctuations caused by changes in traffic conditions such as congestion and bad weather. Moreover, we extract stable and dynamic spatial correlations through our two-stream graph convolutional layer. Finally, we use parameterized skip connection to fuse spatial-temporal correlations as the input of output layer for forecasting. Extensive experiments are conducted on two real-world traffic datasets, and experimental results show that our proposed model is better than several popular baselines.

The popularity of the Internet has brought profound influence to electronic commerce. A kind of review-oriented consumption mode is gradually expanding in the market and consumers will refer to the reviews provided by consumers who bought the product in the past. How to accurately analyze users' sentiments from massive data of e-commerce reviews has become one of the key issues for e-commerce platforms. Current standard sentiment analysis classifies overall sentiment of e-commerce reviews without an extended description of the entity. We set up an optimized Aspect-based sentiment analysis (ABSA) that includes four elements: aspect, category, polarity, and opinion. Aiming at the above problems, this paper proposes a Chinese e-commerce reviews sentiment analysis algorithm based on BERT. By using pre-training model, we use the BIO(B-begin,I-inside,O-outside) data labeling pattern to label entities and study sentiment analysis by the annotation data. Experimental results on the Taobao cosmetics review datasets show that compared with the ordinary deep learning methods, our approach in the accuracy rate and the F1 score has significant improvement.

Banking and Financial Services Corporations need to update information systems with logic and data of various applications on everyday basis to remain consistent with change in economy and business activity. This helps to work with latest information included in information system available in current economic and business scenario. This enables information systems and empowers work force to complete tasks in rapidly changing flow of monetary resources. With several employees in Banking and Financial Services Corporations using cloud infrastructure and reporting incidents arising in using cloud infrastructure, it is of prime importance to fix incidents reported within specific timelines. IT change management process is followed in order to adhere to IT governance & compliance framework and reduce risk of failure while performing changes in cloud infrastructure. With incident management and change management processes are aligned to keep cloud infrastructure available and secure, they become integral part of IT operations everyday activity. To make ITIL processes efficient, further organization specific policies are developed. With global standards and organization level controls in place, there are failures in IT incident and change management processes and implementation. In this paper, we have identified the risk arising due to incident management and change management processes that lead to emergency changes being implemented on cloud infrastructure architecture and discussed the steps to mitigate risks to bring greater responsibility and accountability for cloud services providers.

Text classification (a.k.a text categorisation) is an effective and efficient technology for information organisation and management. With the explosion of information resources on the Web and corporate intranets continues to increase, it has being become more and more important and has attracted wide attention from many different research fields. In the literature, many feature selection methods and classification algorithms have been proposed. It also has important applications in the real world. However, the dramatic increase in the availability of massive text data from various sources is creating a number of issues and challenges for text classification such as scalability issues. The purpose of this report is to give an overview of existing text classification technologies for building more reliable text classification applications, to propose a research direction for addressing the challenging problems in text mining.

Cloud architecture infrastructure for Banking and Financial Services Corporations operates on access control mechanism and trust over various cloud user. Having established the on demand service delivery model to operate, maintain, control and govern the cloud architecture, Banking and Financial Services Corporations deliver round the clock services to customers. Despite stringent security controls and minimum access level, the cloud users identify and exploit the cloud vulnerabilities. This leads to data leakages and loss of critical information. Depending upon the area of business and sophistication with which vulnerabilities have been exploited, frauds are committed and system are damaged by employees and third party contractors. The reason for such exploitation ranges from disgruntlement to personal issues of employees and third party contractors. In this paper, we have identified the various types of insiders, their motives, risk associated with information systems and methods of mitigation in Banking and Financial Services Corporations.

Information systems over cloud architecture infrastructure for Banking and Financial Services Corporations are under constant monitoring by IT security team. This monitoring is to keep check for vulnerabilities, security breach incidents and intrusion in cloud environments and network. IT security team are equipped with sophisticated monitoring tools and empowered to take action in the event of security breach or cyber-attack. This gives IT security team privilege access rights to block and investigate attachments, data packets and logs of various users of cloud infrastructure. The investigation may involve or provide access to the private information of the users. This information can be in emails, files & folders, personal documents and messenger history. In such events, IT security teams are supposed to follow ethical standards established by organization and show high integrity to keep privacy of the cloud users and confidentiality of the investigation. In this paper, we have identified the roles & responsibilities and ethical behaviour expected from IT security teams. This paper also enlists various events that demand ethical behaviour from IT security teams in Banking and Financial Services Corporations.

Cloud computing architecture and infrastructure has received an acceptance from corporations and governments across the globe. Cloud computing helped to reduce cost of management of physical and technical infrastructure at the same time has made information systems available for locally & globally deployed work force. Cloud computing infrastructure provides access to data and applications from any location and this has made organizations to keep evaluating privacy and security framework. Banking and financial services have data and applications which are internally developed to remain ahead of competition. This data and applications becomes the Intellectual Property (IP) that serves specific business processes and goals. When this data and applications can be accessed from remote locations, there may be a potential risks of data leakages and erosion of IP over a period of time. With an adoption of cloud computing, banking and financial services industry continues to be under strict regulatory and compliance framework to maintain privacy of data and security of systems. Privacy and security of cloud architecture infrastructure continues to be the challenge across the globe. In this paper, various aspects of cloud computing related to data privacy and system security for banking and financial services industry have been introduced.

Many of social media platforms such as Facebook and Twitter make it easy for everyone to share their thoughts on literally anything. Topic and opinion detection in social media facilitates the identification of emerging societal trends, analysis of public reactions to policies and business products. In this paper, we proposed a new method that combines the opining mining and context-based topic modelling to analyse public opinions on social media data. Context based topic modelling is used to categorise data in groups and discover hidden communities in data group. The unwanted data group discovered by the topic model then will be discarded. A lexicon based opinion mining method will be applied to the remaining data groups to spot out the public sentiment about the entities. A set of Tweets data on Australian Federal Election 2010 was used in our experiments. Our experimental results demonstrate that, with the help of topic modelling, our social media analysis model is accurate and effective.

Sensor networks usually generate mass of data, which if not structured for future applications, will require much effort on analytical processing and interpretations. Thus, storing sensor data in an effective and structured format is a key issue in the area of sensor networks. In the meantime, even a little improvement on data storing structure may lead to a significant effect on the lifetime and performance of the sensor network. This paper describes a new method for sensor storage that combines semantic web concepts, a data aggregation method along with aligning sensors in hierarchical form. This solution is able to reduce the amount of data stored at the sink nodes significantly. At the same time, the method structures sensed data in a way that we can respond to semantic web-based queries with less consumption of energy compared to previous conventional methods. Results show that, in some situations especially when the diversity of query responses and life of network are vital, the efficiency of our new solution is much better.

Technology plays an important role in helping organizations control quality and costs, and take advantage of opportunities in a highly competitive and increasingly complex business environment. Cloud computing offers greater access to computing power, storage, software, and remote data centres thro ugh the web. This research aims to confirm the factors to be considered for cloud computing adoption in Australian regional municipal governments. The research involved data from interviews with IT managers from selected regional municipal governments, and survey data from 480 IT staff across 47 regional municipal governments. The major factors to be considered for the adoption of cloud computing in regional municipal governments were identified as Internet connectivity, Internet speed, availability, reliability, data storage location, security, data sovereignty, cost, integration, data backup, provider dependability, employees’ knowledge, and transportability. The findings of this research may help managers increase their awareness about factors to be considered when regional municipal governments planning to adopt cloud computing.

The use of intelligent technologies for providing useful recommendations to patients suffering chronic diseases may play a positive role in improving the general life quality of patients and help reduce the workload and cost involved in their daily healthcare. The objective of this study is to deve lop an intelligent recommender system based on predictive analysis for advising patients in the telehealth environment concerning whether they need to take the body test one day in advance by analyzing medical measurements of a patient for the past k days. The proposed algorithms supporting the recommender system have been validated using a time series telehealth data recorded from heart disease patients which were collected from May to January 2012, from our industry collaborator Tunstall. The experimental results show that the proposed system yields satisfactory recommendation accuracy and offer a promising way for saving the workload for patients to conduct body tests every day. This study highlights the possible usefulness of the computerized analysis of time series telehealth data in providing appropriate recommendations to patients suffering chronic diseases such as heart diseases patients.

This paper tackles the key scheduling problem of reducing the overall wait time of mobile clients in wireless data broadcast systems. It is observed that in periodic broadcast, new mobile clients may join in and existing mobile clients may leave anytime; in on-demand broadcast, high uplink communication cost may occur as all clients have to submit their queries every time. These are likely to degrade existing broadcasting approaches. In this work, we study the scheduling problem of XML data broadcast in a hybrid mode, where the system supports both periodic broadcast and on-demand broadcast services at the same. By taking the structural similarity between XML documents into account, only a small portion of mobile clients would be involved in the scheduling process and all mobile clients can be served more effectively. In this way, communication cost at the client side can be reduced greatly. A formal theoretical analysis of the proposed technique is presented. Based on the analysis, a novel clustering-based scheduling algorithm is developed. Moreover, we utilize an aging method to predict the distribution of incoming queries based on small samples of queries from mobile clients. Finally, we evaluate the approach through a set of experiments and the results show that it can significantly improve access efficiency for mobile clients.

Motivated by applications in social networks, a new type of dominating set named Positive Influence Dominating Set (PIDS) has been studied in the literature. In this paper, we investigate cooperative cost games arising from PIDS problem on social network graphs. We propose two new game models, Rigid PIDS Game and Relaxed PIDS Game, and focus on their cores. First, a relationship between the cores of both games is obtained. Next, we also prove that the core of the relaxed PIDS game is nonempty if and only if there is no integrality gap for the relaxation linear programming of the PIDS problem on graph G.

A lot of self-stabilizing algorithms for computing dominating sets problem have been proposed in the literature due to many real-life applications. Most of the proposed algorithms either work for dominating sets with a uniform weight or find approximation solutions to weighted dominating sets. However, for non-uniform weighted dominating sets (WDS) problem, there is no self-stabilizing algorithm for the WDS. Furthermore, how to find the minimal weighted dominating set is a challenge. In this paper, we propose a self-stabilizing algorithm for the minimal weighted dominating set (MWDS) under a central daemon model when operating in any general network. We further prove that the worst case convergence time of the algorithm from any arbitrary initial state is O(n2) steps where n is the number of nodes in the network.

Sentiment analysis or opinion mining is an important type of text analysis that aims to support decision making by extracting and analyzing opinion oriented text, identifying positive and negative opinions, and measuring how positively or negatively an entity (i.e., people, organization, event, location, product, topic, etc.) is regarded. As more and more users express their political and religious views on Twitter, tweets become valuable sources of people's opinions. Tweets data can be efficiently used to infer people's opinions for marketing or social studies. This paper proposes a Tweets Sentiment Analysis Model (TSAM) that can spot the societal interest and general people's opinions in regard to a social event. In this paper, Australian federal election 2010 event was taken as an example for sentiment analysis experiments. We are primarily interested in the sentiment of the specific political candidates, i.e., two primary minister candidates - Julia Gillard and Tony Abbot. Our experimental results demonstrate the effectiveness of the system.

Outlier detection is an important long-standing research problem in data mining and has enjoyed applications in a wide range of applications in business, engineering, biology and security, etc. However, the traditional outlier detection methods inevitably need to use different parameters for detection such as those used to specify the distance or density cutoff for distinguish outliers from normal data points. Using the trial and error approach, the traditional outlier detection methods are rather tedious in parameter tuning. In this demo proposal, we introduce an innovative outlier detection system, called SODIT, that uses localized thresholding to assist the value specification of the thresholds that reflect closely the local data distribution. In addition, easy-to-use user feedback are employed to further facilitate the determination of optimal parameter values. SODIT is able to make outlier detection much easier to operate and produce more accurate, intuitive and informative results than before.

Finding and labelling semantic features patterns of documents in a large, spatial corpus is a challenging problem. Text documents have characteristics that make semantic labelling difficult, the rapidly increasing volume of online documents makes a bottleneck in finding meaningful textual patterns. Aiming to deal with these issues, we propose an unsupervised documnent labelling approach based on semantic content and feature patterns. A world ontology with extensive topic coverage is exploited to supply controlled, structured subjects for labelling. An algorithm is also introduced to reduce dimensionality based on the study of ontological structure. The proposed approach was promisingly evaluated by compared with typical machine learning methods including SVMs, Rocchio, and kNN.

This paper proposes a framework for privacy preserving access control policies and mechanisms, and describes algorithms for access policy conflicting problems. The mechanism enforces access policy to data containing personally identifiable information. The key component of the framework is purpose involved access control models (PAC) that provide full support for expressing highly complex privacy-related policies, taking into account features like purposes, conditions and obligations. Policy conflicting problems may arise when new access policies are generated that are possible to be conflicted to existing policies. As a result of the policy conflicts, private information cannot be well protected. The structure of access control policy including conditions and obligations is studied. Based on the access policy, authorization models and policy operations are analysed. Finally comparisons to related works EPAL are presented.

To detect and annotate the key events of live sports videos, we need to tackle the semantic gaps of audio-visual information. Previous work has successfully extracted semantic from the time-stamped web match reports, which are synchronized with the video contents. However, web and social media articles with no time-stamps have not been fully leveraged, despite they are increasingly used to complement the coverage of major sporting tournaments. This paper aims to address this limitation using a novel multimodal summarization framework that is based on sentiment analysis and players' popularity. It uses audiovisual contents, web articles, blogs, and commentators' speech to automatically annotate and visualize the key events and key players in a sports tournament coverage. The experimental results demonstrate that the automatically generated video summaries are aligned with the events identified from the official website match reports.

As a model for knowledge description and formalization, ontologies are widely used to represent user profiles in personalized web information gathering. However, when representing user profiles, many models have utilized only knowledge from either a global knowledge base or a user local information. In this paper, a personalized ontology model is proposed for knowledge representation and reasoning over user profiles. This model learns ontological user profiles from both a world knowledge base and user local instance repositories. The ontology model is evaluated by comparing it against benchmark models in web information gathering. The results show that this ontology model is successful.

Intelligent agents are an advanced technology utilized in Web Intelligence. When searching information from a distributed Web environment, information is retrieved by multi-agents on the client site and fused on the broker site. The current information fusion techniques rely on cooperation of agents to provide statistics. Such techniques are computationally expensive and unrealistic in the real world. In this paper, we introduce a model that uses a world ontology constructed from the Dewey Decimal Classification to acquire user profiles. By search using specific and exhaustive user profiles, information fusion techniques no longer rely on the statistics provided by agents. The model has been successfully evaluated using the large INEX data set simulating the distributed Web environment.

Nowadays, how to gather useful and meaningful information from the Web has become challenging to all users because of the explosion in the amount of Web information. However, the mainstream of Web information gathering techniques has many drawbacks,

Many data mining techniques have been proposed for mining useful patterns in databases. However, how to effectively utilize discovered patterns is still an open research issue, especially in the domain of text mining. Most existing methods adopt term-based approaches. However, they all suffer from the problems of polysemy and synonymy. This paper presents an innovative technique, pattern taxonomy mining, to improve the effectiveness of using discovered patterns for finding useful information. Substantial experiments on RCV1 demonstrate that the proposed solution achieves encouraging performance.

Retrieving accurate information from the Web is a great challenge to users. The existing information retrieval systems are mostly term-based and thus need to be enhanced toward knowledge-based. User information needs need to be better captured in order to deliver personalized search results. In this paper, an ontology-based framework is proposed for capturing user information needs using a world knowledge base and the user's local instance repository. The framework aims to discover a user's background knowledge for knowledge retrieval. The evaluation result is encouraging, in which the proposed model achieved the same performance as a manual user model.

It is well accepted that ontology is useful for personalized Web information gathering. However, it is challenging to use semantic relations of "kind-of", "part-of", and "related-to" and synthesize commonsense and expert knowledge in a single computational model. In this paper, a personalized ontology model is proposed attempting to answer this challenge. A two-dimensional (Exhaustivity and Specificity) method is also presented to quantitatively analyze these semantic relations in a single framework. The proposals are successfully evaluated by applying the model to a Web information gathering system. The model is a significant contribution to personalized ontology engineering and concept-based Web information gathering in Web Intelligence.

The traditional techniques rely on human effort to acquire training sets, which is expensive and inefficient. In this paper we present an alternative method to automatically acquire training sets without heavy investment of user efforts. The proposed method tends to fill a gap for effectiveness of using Web data in Web mining, and contributes to Web information gathering. The evaluation shows that the method is adequate to yield an promising achievement.