While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption attacks. Adversaries exploit these vulnerabilities by poisoning documents provided by RAG system to manipulate LLM outputs. To counter this threat, we propose SecureCollaRAG, a Byzantine-tolerant collaborative RAG framework leveraging Multi-source Knowledge Validation Mechanism. Our approach enables agent system to securely verify document provenance through dynamic GNN-based credibility scoring, effectively preventing stealthy knowledge corruption attacks while preserving essential domain knowledge integrity. Through extensive evaluations and formal analysis, we demonstrate that SecureCollaRAG maintains robustness against attackers under non-IID data distributions.

Event extraction (EE) is one of the key tasks in information extraction, aiming to automatically identify events and their corresponding arguments from text. Previous EE work has primarily focused on flat events, often overlooking the challenges related to overlapping and nested events. To tackle this issue, we propose a new approach that combines the large language models(LLMs) and the small language models(SLMs) to address overlapping and nested events. The LLMs capture rich prior information from text and use it as a local information prompt. The SLMs use the global event type prompt to better understand the semantic information of the events. We refer to this approach as a D ual-Prompt framework for overlapping and nested E vent E xtraction (DPEE). By capturing dual-prompt features, DPEE effectively enhances event decoding capabilities. Experiments on the public EE datasets FewFC and FNDEE show that our event extraction method achieves significant improvements.

The cloud-edge-end collaboration framework is emerging as a promising means to handle diverse tasks and improve Quality of Service. Existing research rarely considers the affinity between diverse tasks and heterogeneous resources, preventing the further improvement of system performance. This paper proposes a dynamic task scheduling approach based on the intelligent affinity strategy for cloud-edge-end collaboration. The affinity strategy depicts the preference of tasks for computing nodes with different labels, including resource types and node zones, and each task can set multiple affinity rules to match target nodes. Additionally, the proposed approach adopts deep reinforcement learning theory to generate the affinity rules, which means utilizing an intelligent algorithm to guide the rule generation. Extensive experiments show that the proposed approach can reduce the average cost by at least 20% compared with the baseline.

Edge computing has become a promising technology to mitigate the latency of various cloud services. Task scheduling in edge computing is challenging due to the heterogeneous devices and multiple tasks. This paper proposes an affinity-based scheduling algorithm to solve the multi-task scheduling problem with heterogeneous computing resources under edge computing. The algorithm uses a centralized scheduling strategy that takes into account the overall matching between intelligent computing tasks and heterogeneous resources from two aspects: resource affinity and system load balancing. It can adjust the weights among these aspects to meet different application requirements. The results show that the proposed algorithm can reduce the average response time by at least 10% and has a significant advantage regarding the system running time compared to the other comparative methods.

It is important to minimize the energy consumption of large-scale, geographically distributed edge data centers (EDCs). While modern processing units (PUs) have energy-saving features like Dynamic Voltage and Frequency Scaling (DVFS) and Per-Core Power Gating (PCPG), optimization is still complex and requires a holistic approach. This article presents a new decentralized, three-timescale, online optimization approach that enables multicore micro data centers (MDCs) to optimize their per-PU power states, per-enabled-PU voltage-frequency levels and offloading schedules at three different timescales. The key idea is that we employ multi-timescale Lyapunov optimization to decouple the energy minimization between workload scheduling and result delivery at a small timescale and PU configuration at large timescales. Another important aspect is that we apply the primal decomposition to decouple the PU configuration between a per-enabled-PU voltage-frequency level at an intermediate timescale and a per-PU power state at a large timescale. Experiments demonstrate that the proposed approach improves energy efficiency significantly by up to 4.5 times in our considered lightly loaded situations where DVFS alone does not work effectively, compared to existing benchmarks.

The mobile social network contains a large amount of information in a form of commentary. Effective analysis of the sentiment in the comments would help improve the recommendations in the mobile network. With the development of well‐performing pretrained language models, the performance of sentiment classification task based on deep learning has seen new breakthroughs in the past decade. However, deep learning models suffer from poor interpretability, making it difficult to integrate sentiment knowledge into the model. This paper proposes a sentiment classification model based on the cascade of the BERT model and the adaptive sentiment dictionary. First, the pretrained BERT model is used to fine‐tune with the training corpus, and the probability of sentiment classification in different categories is obtained through the softmax layer. Next, to allow a more effective comparison between the probabilities for the two classes, a nonlinearity is introduced in a form of positive‐negative probability ratio, using the rule method based on sentiment dictionary to deal with the probability ratio below the threshold. This method of cascading the pretrained model and the semantic rules of the sentiment dictionary allows to utilize the advantages of both models. Different sized Chnsenticorp data sets are used to train the proposed model. Experimental results show that the Dict‐BERT model is better than the BERT‐only model, especially when the training set is relatively small. The improvement is obvious with the accuracy increase of 0.8%.

Smart device users spend most of the fragmentation time in the entertainment applications such as videos and films. The migration and reconstruction of video copies can improve the storage efficiency in distributed mobile edge computing, and the prediction of video hits is the premise for migrating video copies. This paper proposes a new prediction approach for video hits based on the combination of correlation analysis and wavelet neural network (WNN). This is achieved by establishing a video index quantification system and analyzing the correlation between the video to be predicted and already online videos. Then, the similar videos are selected as the influencing factors of video hits. Compared with the autoregressive integrated moving average (ARIMA) and gray prediction, the proposed approach has a higher prediction accuracy and a broader application scope.

This paper focuses on matching ontologies created for similar domains through different sources. Different solutions use lexical, structural or logical processing and analysis to match ontologies. However, an important aspect is also interpreting concepts that entities are presented with and using them in relation to semantics in an ontology. The paper demonstrates analyzing and extending the concepts used to define entities in an ontology, discusses establishing and filtering matching candidates by reasoners, and then describes constructing correspondences between entities from different ontologies using lexical and semantic analysis. The experiments show that our prototype, called OMI-DL, is among the top group over many ontologies adopted from the OAEI benchmark data set. We also provide an evaluation of the OMI-DL method for matching the DOLCE+DnS Ultralite ontology and the domain ontology developed in the m:Ciudad project.

Aligning different ontologies from similar (or same) domains is an active field of current research. There are various solutions which process and analyze lexical, structural or semantic information to align ontologies. However, there are few solutions that focus on interpreting the concepts that entities are presented with and using them in relation to the semantics implied in an ontology. In this paper, the prototype (OACLAI) is presented to tackle this by combining lexical analysis with consequences from reasoners which reflect the semantics implied in an ontology. We evaluate OACLAI over the four real ontologies and compare it against the seven solutions. The experiments show that the accuracy of OACLAI is higher than those of others on average.