Searcharxiv⌕ Search

arXiv subjects

Jinfeng Zhong

Publications and source records attributed to Jinfeng Zhong.

9 recordsLinked to original sources
arXiv2026

Cast: Automated Resilience Testing for Production Cloud Service Systems

The distributed nature of microservice architecture introduces significant resilience challenges. Traditional testing methods, limited by extensive manual effort and oversimplified test environments, fail to capture production system complexity. To address these limitations, we present Cast, an automated, end-to-end framework for microservice resilience testing in production. It achieves high test fidelity by replaying production traffic against a comprehensive library of application-level faults to exercise internal error-handling logic. To manage the combinatorial test space, Cast employs a complexity-driven strategy to systematically prune redundant tests and prioritize high-value tests targeting the most critical service execution paths. Cast automates the testing lifecycle through a three-phase pipeline (i.e., startup, fault injection, and recovery) and uses a multi-faceted oracle to automatically verify system resilience against nuanced criteria. Deployed in Huawei Cloud for over eight months, Cast has been adopted by many service teams to proactively address resilience vulnerabilities. Our analysis on four large-scale applications with millions of traces reveals 137 potential vulnerabilities, with 89 confirmed by developers. To further quantify its performance, Cast is evaluated on a benchmark set of 48 reproduced bugs, achieving a high coverage of 90%. The results show that Cast is a practical and effective solution for systematically improving the reliability of industrial microservice systems.

cs.SE↗
arXiv2025

KANFormer for Predicting Fill Probabilities via Survival Analysis in Limit Order Books

This paper introduces KANFormer, a novel deep-learning-based model for predicting the time-to-fill of limit orders by leveraging both market- and agent-level information. KANFormer combines a Dilated Causal Convolutional network with a Transformer encoder, enhanced by Kolmogorov-Arnold Networks (KANs), which improve nonlinear approximation. Unlike existing models that rely solely on a series of snapshots of the limit order book, KANFormer integrates the actions of agents related to LOB dynamics and the position of the order in the queue to more effectively capture patterns related to execution likelihood. We evaluate the model using CAC 40 index futures data with labeled orders. The results show that KANFormer outperforms existing works in both calibration (Right-Censored Log-Likelihood, Integrated Brier Score) and discrimination (C-index, time-dependent AUC). We further analyze feature importance over time using SHAP (SHapley Additive exPlanations). Our results highlight the benefits of combining rich market signals with expressive neural architectures to achieve accurate and interpretabl predictions of fill probabilities.

cs.AI↗
arXiv2024

Fuzzy synthetic method for evaluating explanations in recommender systems

Recommender systems aim to help users find relevant items more quickly by providing personalized recommendations. Explanations in recommender systems help users understand why such recommendations have been generated, which in turn makes the system more transparent and promotes users' trust and satisfaction. In recent years, explaining recommendations has drawn increasing attention from both academia and from industry. In this paper, we present a user study to investigate context-aware explanations in recommender systems. In particular, we build a web-based questionnaire that is able to interact with users: generating and explaining recommendations. With this questionnaire, we investigate the effects of context-aware explanations in terms of efficiency, effectiveness, persuasiveness, satisfaction, trust and transparency through a user study. Besides, we propose a novel method based on fuzzy synthetic evaluation for aggregating these metrics.

cs.HC↗
arXiv2024

When factorization meets argumentation: towards argumentative explanations

Factorization-based models have gained popularity since the Netflix challenge {(2007)}. Since that, various factorization-based models have been developed and these models have been proven to be efficient in predicting users' ratings towards items. A major concern is that explaining the recommendations generated by such methods is non-trivial because the explicit meaning of the latent factors they learn are not always clear. In response, we propose a novel model that combines factorization-based methods with argumentation frameworks (AFs). The integration of AFs provides clear meaning at each stage of the model, enabling it to produce easily understandable explanations for its recommendations. In this model, for every user-item interaction, an AF is defined in which the features of items are considered as arguments, and the users' ratings towards these features determine the strength and polarity of these arguments. This perspective allows our model to treat feature attribution as a structured argumentation procedure, where each calculation is marked with explicit meaning, enhancing its inherent interpretability. Additionally, our framework seamlessly incorporates side information, such as user contexts, leading to more accurate predictions. We anticipate at least three practical applications for our model: creating explanation templates, providing interactive explanations, and generating contrastive explanations. Through testing on real-world datasets, we have found that our model, along with its variants, not only surpasses existing argumentation-based methods but also competes effectively with current context-free and context-aware methods.

cs.AI↗
arXiv2023

Context-aware explainable recommendations over knowledge graphs

Knowledge graphs contain rich semantic relationships related to items and incorporating such semantic relationships into recommender systems helps to explore the latent connections of items, thus improving the accuracy of prediction and enhancing the explainability of recommendations. However, such explainability is not adapted to users' contexts, which can significantly influence their preferences. In this work, we propose CA-KGCN (Context-Aware Knowledge Graph Convolutional Network), an end-to-end framework that can model users' preferences adapted to their contexts and can incorporate rich semantic relationships in the knowledge graph related to items. This framework captures users' attention to different factors: contexts and features of items. More specifically, the framework can model users' preferences adapted to their contexts and provide explanations adapted to the given context. Experiments on three real-world datasets show the effectiveness of our framework: modeling users' preferences adapted to their contexts and explaining the recommendations generated.

cs.IR↗
arXiv2023

Context-aware feature attribution through argumentation

Feature attribution is a fundamental task in both machine learning and data analysis, which involves determining the contribution of individual features or variables to a model's output. This process helps identify the most important features for predicting an outcome. The history of feature attribution methods can be traced back to General Additive Models (GAMs), which extend linear regression models by incorporating non-linear relationships between dependent and independent variables. In recent years, gradient-based methods and surrogate models have been applied to unravel complex Artificial Intelligence (AI) systems, but these methods have limitations. GAMs tend to achieve lower accuracy, gradient-based methods can be difficult to interpret, and surrogate models often suffer from stability and fidelity issues. Furthermore, most existing methods do not consider users' contexts, which can significantly influence their preferences. To address these limitations and advance the current state-of-the-art, we define a novel feature attribution framework called Context-Aware Feature Attribution Through Argumentation (CA-FATA). Our framework harnesses the power of argumentation by treating each feature as an argument that can either support, attack or neutralize a prediction. Additionally, CA-FATA formulates feature attribution as an argumentation procedure, and each computation has explicit semantics, which makes it inherently interpretable. CA-FATA also easily integrates side information, such as users' contexts, resulting in more accurate predictions.

cs.LG↗
arXiv2023

CORec-Cri: How collaborative and social technologies can help to contextualize crises?

Crisis situations can present complex and multifaceted challenges, often requiring the involvement of multiple organizations and stakeholders with varying areas of expertise, responsibilities, and resources. Acquiring accurate and timely information about impacted areas is crucial to effectively respond to these crises. In this paper, we investigate how collaborative and social technologies help to contextualize crises, including identifying impacted areas and real-time needs. To this end, we define CORec-Cri (Contextulized Ontology-based Recommender system for crisis management) based on existing work. Our motivation for this approach is two-fold: first, effective collaboration among stakeholders is essential for efficient and coordinated crisis response; second, social computing facilitates interaction, information flow, and collaboration among stakeholders. We detail the key components of our system design, highlighting its potential to support decision-making, resource allocation, and communication among stakeholders. Finally, we provide examples of how our system can be applied to contextualize crises to improve crisis management.

cs.CY↗
arXiv2023

Constraint-based recommender system for crisis management simulations

In the context of the evacuation of populations, some citizens/volunteers may want and be able to participate in the evacuation of populations in difficulty by coming to lend a hand to emergency/evacuation vehicles with their own vehicles. One way of framing these impulses of solidarity would be to be able to list in real-time the citizens/volunteers available with their vehicles (land, sea, air, etc.), to be able to geolocate them according to the risk areas to be evacuated, and adding them to the evacuation/rescue vehicles. Because it is difficult to propose an effective real-time operational system on the field in a real crisis situation, in this work, we propose to add a module for recommending driver/vehicle pairs (with their specificities) to a system of crisis management simulation. To do that, we chose to model and develop an ontology-supported constraint-based recommender system for crisis management simulations.

cs.IR↗
arXiv2023

Système de recommandations basé sur les contraintes pour les simulations de gestion de crise

In the context of the evacuation of populations, some citizens/volunteers may want and be able to participate in the evacuation of populations in difficulty by coming to lend a hand to emergency/evacuation vehicles with their own vehicles. One way of framing these impulses of solidarity would be to be able to list in real-time the citizens/volunteers available with their vehicles (land, sea, air, etc.), to be able to geolocate them according to the risk areas to be evacuated, and adding them to the evacuation/rescue vehicles. Because it is difficult to propose an effective real-time operational system on the field in a real crisis situation, in this work, we propose to add a module for recommending driver/vehicle pairs (with their specificities) to a system of crisis management simulation. To do that, we chose to model and develop an ontology-supported constraint-based recommender system for crisis management simulations.

cs.IR↗