ACM Transactions on Intelligent Systems and Technology最新文献

Service composition platforms play a crucial role in creating personalized service processes. Challenges, including the risk of tampering with service data during service invocation and the potential single point of failure in centralized service registration centers, hinder the efficient and responsible creation of service processes. This paper presents a novel framework called Context-Aware Responsible Service Process Creation and Recommendation (SPCR-CA), which incorporates blockchain, Recurrent Neural Networks (RNNs), and a Skip-Gram model holistically to enhance the security, efficiency, and quality of service process creation and recommendation. Specifically, the blockchain establishes a trusted service provision environment, ensuring transparent and secure transactions between services and mitigating the risk of tampering. The RNN trains responsible service processes, contextualizing service components and producing coherent recommendations of linkage components. The Skip-Gram model trains responsible user-service process records, generating semantic vectors that facilitate the recommendation of similar service processes to users. Experiments using the Programmable-Web dataset demonstrate the superiority of the SPCR-CA framework to existing benchmarks in precision and recall. The proposed framework enhances the reliability, efficiency, and quality of service process creation and recommendation, enabling users to create responsible and tailored service processes. The SPCR-CA framework offers promising potential to provide users with secure and user-centric service creation and recommendation capabilities.

Popularity bias is the tendency of recommender systems to further suggest popular items while disregarding niche ones, hence giving no chance for items with low popularity to emerge. Although the literature is rich in debiasing techniques, it still lacks quality measures that effectively enable their analyses and comparisons.

In this paper, we first introduce a formal, data-driven, and parameter-free strategy for classifying items into low, medium, and high popularity categories. Then we introduce BQS, a quality measure that rewards the debiasing techniques that successfully push a recommender system to suggest niche items, without losing points in its predictive capability in terms of global accuracy.

We conduct tests of BQS on three distinct baseline collaborative filtering (CF) frameworks: one based on history-embedding and two on user/item-embedding modeling. These evaluations are performed on multiple benchmark datasets and against various state-of-the-art competitors, demonstrating the effectiveness of BQS.

Emotion recognition has attracted a lot of interest in recent years in various application areas such as healthcare and autonomous driving. Existing approaches to emotion recognition are based on visual, speech, or psychophysiological signals. However, recent studies are looking at multimodal techniques that combine different modalities for emotion recognition. In this work, we address the problem of recognizing the user’s emotion as a driver from unlabeled videos using multimodal techniques. We propose a collaborative training method based on cross-modal distillation, i.e., ”FedCMD” (Federated Cross-Modal Distillation). Federated Learning (FL) is an emerging collaborative decentralized learning technique that allows each participant to train their model locally to build a better generalized global model without sharing their data. The main advantage of FL is that only local data is used for training, thus maintaining privacy and providing a secure and efficient emotion recognition system. The local model in FL is trained for each vehicle device with unlabeled video data by using sensor data as a proxy. Specifically, for each local model, we show how driver emotional annotations can be transferred from the sensor domain to the visual domain by using cross-modal distillation. The key idea is based on the observation that a driver’s emotional state indicated by a sensor correlates with facial expressions shown in videos. The proposed ”FedCMD” approach is tested on the multimodal dataset ”BioVid Emo DB” and achieves state-of-the-art performance. Experimental results show that our approach is robust to non-identically distributed data, achieving 96.67% and 90.83% accuracy in classifying five different emotions with IID (independently and identically distributed) and non-IID data, respectively. Moreover, our model is much more robust to overfitting, resulting in better generalization than the other existing methods.

As one of the fundamental tasks of autonomous driving, depth perception aims to perceive physical objects in three dimensions and to judge their distances away from the ego vehicle. Although great efforts have been made for depth perception, LiDAR-based and camera-based solutions have limitations with low accuracy and poor robustness for noise input. With the integration of monocular cameras and LiDAR sensors in autonomous vehicles, in this paper, we introduce a two-stream architecture to learn the modality interaction representation under the guidance of an image reconstruction task to compensate for the deficiencies of each modality in a parallel manner. Specifically, in the two-stream architecture, the multi-scale cross-modality interactions are preserved via a cascading interaction network under the guidance of the reconstruction task. Next, the shared representation of modality interaction is integrated to infer the dense depth map due to the complementary and the heterogeneity of the two modalities. We evaluated the proposed solution on the KITTI dataset and CALAR synthetic dataset. Our experimental results show that learning the coupled interaction of modalities under the guidance of an auxiliary task can lead to significant performance improvements. Furthermore, our approach is competitive against the state-of-the-art models and robust against the noisy input. The source code is available at https://github.com/tonyFengye/Code/tree/master.

Heterogeneous graph convolutional networks have gained great popularity in tackling various network analytical tasks on heterogeneous graph data, ranging from link prediction to node classification. However, most existing works ignore the relation heterogeneity with multiplex networks between multi-typed nodes and the different importance of relations in meta-paths for node embedding, which can hardly capture the heterogeneous structure signals across different relations. To tackle this challenge, this work proposes a Multiplex Heterogeneous Graph Convolutional Network (MHGCN+) for multiplex heterogeneous network embedding. Our MHGCN+ can automatically learn the useful heterogeneous meta-path interactions of different lengths with different importance in multiplex heterogeneous networks through multi-layer convolution aggregation. Additionally, we effectively integrate both multi-relation structural signals and attribute semantics into the learned node embeddings with both unsupervised and semi-supervised learning paradigms. Extensive experiments on seven real-world datasets with various network analytical tasks demonstrate the significant superiority of MHGCN+ against state-of-the-art embedding baselines in terms of all evaluation metrics. The source code of our method is available at: https://github.com/FuChF/MHGCN-plus.

Despite the benefits of personalizing items and information tailored to users’ needs, it has been found that recommender systems tend to introduce biases that favor popular items or certain categories of items, and dominant user groups. In this study, we aim to characterize the systematic errors of a recommendation system and how they manifest in various accountability issues, such as stereotypes, biases, and miscalibration. We propose a unified framework that distinguishes the sources of prediction errors into a set of key measures that quantify the various types of system-induced effects, both at the individual and collective levels. Based on our measuring framework, we examine the most widely adopted algorithms in the context of movie recommendation. Our research reveals three important findings: (1) Differences between algorithms: recommendations generated by simpler algorithms tend to be more stereotypical but less biased than those generated by more complex algorithms. (2) Disparate impact on groups and individuals: system-induced biases and stereotypes have a disproportionate effect on atypical users and minority groups (e.g., women and older users). (3) Mitigation opportunity: using structural equation modeling, we identify the interactions between user characteristics (typicality and diversity), system-induced effects, and miscalibration. We further investigate the possibility of mitigating system-induced effects by oversampling underrepresented groups and individuals, which was found to be effective in reducing stereotypes and improving recommendation quality. Our research is the first systematic examination of not only system-induced effects and miscalibration but also the stereotyping issue in recommender systems.

Recommender systems have become important tools in the daily life of human beings since they are powerful to address information overload, and discover relevant and useful items for users. The success of recommender systems largely relies on the interaction history between users and items, which is expected to accurately reflect the preferences of users on items. However, the expectation is easily broken in practice, due to the corruptions made in the interaction history, resulting in unreliable and untrusted recommender systems. Previous works either ignore this issue (assume that the interaction history is precise) or are limited to handling additive noise. Motivated by this, in this paper, we study rating flip noise which is widely existed in the interaction history of recommender systems and combat it by modelling the noise generation process. Specifically, the rating flip noise allows a rating to be flipped to any other ratings within the given rating set, which reflects various real-world situations of rating corruption, e.g., a user may randomly click a rating from the rating set and then submit it. The noise generation process is modelled by the noise transition matrix that denotes the probabilities of a clean rating flip into a noisy rating. A statistically consistent algorithm is afterwards applied with the estimated transition matrix to learn a robust recommender system against rating flip noise. Comprehensive experiments on multiple benchmarks confirm the superiority of our method.

Human beings always engage in a vast range of activities and tasks that demonstrate their ability to adapt to different scenarios. These activities can range from the simplest daily routines, like walking and sitting, to multi-level complex endeavors such as cooking a four-course meal. Any human activity can be represented as a temporal sequence of actions performed to achieve a certain goal. Unlike the time series datasets extracted from electronics or machines, these action sequences are highly disparate in their nature – the time to finish a sequence of actions can vary between different persons. Therefore, understanding the dynamics of these sequences is essential for many downstream tasks such as activity length prediction, goal prediction, next-action recommendation, etc. Existing neural network-based approaches that learn a continuous-time activity sequence (or CTAS) are limited to the presence of only visual data or are designed specifically for a particular task, i.e., limited to next action or goal prediction. In this paper, we present ProActive, a neural marked temporal point process (MTPP) framework for modeling the continuous-time distribution of actions in an activity sequence while simultaneously addressing three high-impact problems – next action prediction, sequence-goal prediction, and end-to-end sequence generation. Specifically, we utilize a self-attention module with temporal normalizing flows to model the influence and the inter-arrival times between actions in a sequence. Moreover, for time-sensitive prediction, we perform an early detection of sequence goal via a constrained margin-based optimization procedure. This in-turn allows ProActive to predict the sequence goal using a limited number of actions. In addition, we propose a novel addition over the ProActive model, called ProActive++, that can handle variations in the order of actions, i.e., different methods of achieving a given goal. We demonstrate that this variant can learn the order in which the person or actor prefers to do their actions. Extensive experiments on sequences derived from three activity recognition datasets show the significant accuracy boost of our ProActive and ProActive++ over the state-of-the-art in terms of action and goal prediction, and the first-ever application of end-to-end action sequence generation.

The availability of large data sets is providing the impetus for driving many current artificial intelligent developments. However, specific challenges arise in developing solutions that exploit small data sets, mainly due to practical and cost-effective deployment issues, as well as the opacity of deep learning models. To address this, the Comprehensive Abstraction and Classification Tool for Uncovering Structures (CACTUS) is presented as a means of improving secure analytics by effectively employing explainable artificial intelligence. CACTUS achieves this by providing additional support for categorical attributes, preserving their original meaning, optimising memory usage, and speeding up the computation through parallelisation. It exposes to the user the frequency of the attributes in each class and ranks them by their discriminative power. Performance is assessed by applying it to various domains, including Wisconsin Diagnostic Breast Cancer, Thyroid0387, Mushroom, Cleveland Heart Disease, and Adult Income data sets.

Recent advancement in deep-neural network performance led to the development of new state-of-the-art approaches in numerous areas. However, the black-box nature of neural networks often prohibits their use in areas where model explainability and model transparency are crucial. Over the years, researchers proposed many algorithms to aid neural network understanding and provide additional information to the human expert. One of the most popular methods being Layer-Wise Relevance Propagation (LRP). This method assigns local relevance based on the pixel-wise decomposition of nonlinear classifiers. With the rise of attribution method research, there has emerged a pressing need to assess and evaluate their performance. Numerous metrics have been proposed, each assessing an individual property of attribution methods such as faithfulness, robustness or localization. Unfortunately, no single metric is deemed optimal for every case, and researchers often use several metrics to test the quality of the attribution maps. In this work, we address the shortcomings of the current LRP formulations and introduce a novel method for determining the relevance of input neurons through layer-wise relevance propagation. Furthermore, we apply this approach to the recently developed Vision Transformer architecture and evaluate its performance against existing methods on two image classification datasets, namely ImageNet and PascalVOC. Our results clearly demonstrate the advantage of our proposed method. Furthermore, we discuss the insufficiencies of current evaluation metrics for attribution-based explainability and propose a new evaluation metric that combines the notions of faithfulness, robustness and contrastiveness. We utilize this new metric to evaluate the performance of various attribution-based methods. Our code is available at: https://github.com/davor10105/relative-absolute-magnitude-propagation