Low-resource languages are challenging to process intelligent decision systems due to limited data and resources. As an effective way of processing low-resource languages in intelligent decision systems, fuzzy linguis...
详细信息
Low-resource languages are challenging to process intelligent decision systems due to limited data and resources. As an effective way of processing low-resource languages in intelligent decision systems, fuzzy linguistic approaches excel in transforming original uncertain linguistic information into highly structured data and learning valid decision rules between complex data structures. However, existing fuzzy linguistic methods may not fully capture realistic features of multi-attribute group decision-making (MAGDM), such as incomplete and hesitant linguistic expressions, stable information fusion, and bounded rationality of decision-makers (DMs). Therefore, it is necessary to develop a collaborative fuzzy language learning system based on bounded rationality, low-resource and robust decision-making. Specifically, we present a new multi-granularity (MG) group decision-making (GDM) scheme by using MULTIMOORA (Multi-Objective Optimization by Ratio Analysis plus the full MULTIplicative form) and PT (Prospect Theory) for incomplete hesitant fuzzy linguistic informationsystems (I-HFL-ISs), where MG GDM aims to discover knowledge from complex MAGDM problems with MG features. To achieve the above goal, we first introduce the concept of MG-I-HFL-ISs to represent incomplete, hesitant and imprecise linguistic evaluation information offered by multiple decision-makers (DMs). Then, we apply a valid transformation scheme to convert MG-I-HFL-ISs into MG-HFL-ISs, and use the MG probability rough set (PRS) to develop a series of MG-HFL-PRSs with the support of MULTIMOORA. Afterwards, an HFL MG GDM method is designed by integrating MULTIMOORA and PT for solving MAGDM problems with MG-I-HFL-ISs. The proposed method can effectively synthesize low-resource languages and mine useful decision-making knowledge. At last, a drug selection case and a simulated case are performed for showing the rationality of the designed HFL MG GDM scheme.
Edge intelligence (EI) integrates edge computing and artificial intelligence empowering service providers to deploy deep neural networks (DNNs) on edge servers in proximity to users to provision intelligent applicatio...
详细信息
Edge intelligence (EI) integrates edge computing and artificial intelligence empowering service providers to deploy deep neural networks (DNNs) on edge servers in proximity to users to provision intelligent applications (e.g., autonomous driving) for ubiquitous Internet of Things (IoT) in smart cities, which facilitates the quality of experience (QoE) of users and improves the processing and energy efficiency. However, considering DNN is typically computational-intensive and resource-hungry, conventional placement approaches ignore the influence of multi-dimensional resource requirements (processor, memory, etc.), which may degrade the real-time performance. Moreover, with the increasing scale of geo-distributed edge servers, centralized decision-making is still challenging to find the optimal strategies effectively. To overcome these shortcomings, in this paper we propose a game theoretic DNN placement approach in EI-enabled IoT. First, a DNN placement optimization problem is formulated to maximize system benefits, which is proven to be \(\mathcal {N}\mathcal {P}\)-hard and model the original problem as an exact potential game (EPG). Moreover, an EPG-based DNN model placement algorithm, named EPOL, is designed for edge servers to make sub-optimal strategies independently and theoretical analysis is possessed to guarantee the performance of EPOL. Finally, real-world dataset based experimental results corroborate the superiority and effectiveness of EPOL.
Fact verification task has emerged as an essential research topic recently due to abundant fake news spreading on the Internet. The task based on unstructured data (i.e., news) has achieved great development, but the ...
详细信息
Fact verification task has emerged as an essential research topic recently due to abundant fake news spreading on the Internet. The task based on unstructured data (i.e., news) has achieved great development, but the task based on structured data (i.e., table) is still in the primary development period. The existing methods usually construct complete heterogeneous graph networks around statement, table, and program subgraphs, and then infer to learn similar semantics on them for fact verification. However, they generally connect the nodes with the same content between subgraphs directly to frame a larger graph network, which has serious sparsity in connections, especially when subgraphs possess limited semantics. To this end, we propose tight-fitting graph inference network (TFGIN), which innovatively builds tight-fitting graphs (TF-graph) to strengthen the connections of subgraphs, and designs inference modeling layer (IML) to learn coherence evidence for fact verification. Specifically, different from traditional connection ways, the constructed TF-graph enhances inter-graph and intra-graph connections of subgraphs through subgraph segmentation and interaction guidance mechanisms. Inference modeling layer could reason the semantics with strong correlation and high consistency as explainable evidence. Experiments on three competitive datasets confirm the superiority and scalability of our TFGIN.
Knowledge graphs have proven highly effective for learning representations of entities and relations, with hyper-relational knowledge graphs (HKGs) gaining increased attention due to their enhanced representation capa...
详细信息
Knowledge graphs have proven highly effective for learning representations of entities and relations, with hyper-relational knowledge graphs (HKGs) gaining increased attention due to their enhanced representation capabilities. Each fact in an HKG consists of a main triple supplemented by attribute-value qualifiers that provide additional contextual information. Due to the complexity of hyper-relations, HKGs typically contain complex geometric structures, such as hierarchical, ring, and chain structures, often mixed together. However, previous work mainly embeds HKGs into Euclidean space, limiting their ability to capture these complex geometric structures simultaneously. To address this challenge, we propose a novel model called Geometry Aware Hyper-relational Embedding (GAHE). Specifically, GAHE adopts a multi-curvature geometry-aware approach by modeling HKGs in Euclidean space (zero curvature), hyperbolic space (negative curvature), and hyperspherical space (positive curvature) in a unified framework. In this way, it can integrate space-invariant and space-specific features to accurately capture the diverse structures in HKGs. In addition, GAHE introduces a module termed hyper-relational subspace learning, which allocates multiple sub-relations for each hyper-relation. It enables the exploitation of abundant latent semantic interactions and facilitates the exploration of fine-grained semantics between attribute-value pairs and hyper-relations across multiple subspaces. Furthermore, we provide theoretical guarantees that GAHE is fully expressive and capable of modeling a wide range of semantic patterns for hyper-relations. Empirical evaluations demonstrate that GAHE achieves state-of-the-art results on both hyper-relational and binary-relational benchmarks.
This book constitutes the refereed proceedings of the 14th International Conference on informationsecurity, ISC 2011, held in Xi'an, China, in October 2011. The 25 revised full papers were carefully reviewed and ...
详细信息
ISBN:
(数字)9783642248610
ISBN:
(纸本)9783642248603
This book constitutes the refereed proceedings of the 14th International Conference on informationsecurity, ISC 2011, held in Xi'an, China, in October 2011. The 25 revised full papers were carefully reviewed and selected from 95 submissions. The papers are organized in topical sections on attacks; protocols; public-key cryptosystems; network security; software security; systemsecurity; database security; privacy; digital signatures.
Connected Autonomous Vehicle (CAV) Driving, as a data-driven intelligent driving technology within the Internet of Vehicles (IoV), presents significant challenges to the efficiency and security of real-time data manag...
详细信息
Connected Autonomous Vehicle (CAV) Driving, as a data-driven intelligent driving technology within the Internet of Vehicles (IoV), presents significant challenges to the efficiency and security of real-time data management. The combination of Web3.0 and edge content caching holds promise in providing low-latency data access for CAVs’ real-time applications. Web3.0 enables the reliable pre-migration of frequently requested content from content providers to edge nodes. However, identifying optimal edge node peers for joint content caching and replacement remains challenging due to the dynamic nature of traffic flow in IoV. Addressing these challenges, this article introduces GAMA-Cache, an innovative edge content caching methodology leveraging Graph Attention Networks (GAT) and Multi-Agent Reinforcement Learning (MARL). GAMA-Cache conceptualizes the cooperative edge content caching issue as a constrained Markov decision process. It employs a MARL technique predicated on cooperation effectiveness to discern optimal caching decisions, with GAT augmenting information extracted from adjacent nodes. A distinct collaborator selection mechanism is also developed to streamline communication between agents, filtering out those with minimal correlations in the vector input to the policy network. Experimental results demonstrate that, in terms of service latency and delivery failure, the GAMA-Cache outperforms other state-of-the-art MARL solutions for edge content caching in IoV.
Non-overlapping Cross-domain Sequential Recommendation (NCSR) is the task that focuses on domain knowledge transfer without overlapping entities. Compared with traditional Cross-domain Sequential Recommendation (CSR),...
详细信息
Non-overlapping Cross-domain Sequential Recommendation (NCSR) is the task that focuses on domain knowledge transfer without overlapping entities. Compared with traditional Cross-domain Sequential Recommendation (CSR), NCSR poses several challenges: 1) NCSR methods often rely on explicit item IDs, overlooking semantic information among entities. 2) Existing CSR mainly relies on domain alignment for knowledge transfer, risking semantic loss during alignment. 3) Most previous studies do not consider the many-to-one characteristic, which is challenging because of the utilization of multiple source domains. Given the above challenges, we introduce the prompt learning technique for Many-to-one Non-overlapping Cross-domain Sequential Recommendation (MNCSR) and propose a Text-enhanced Co-attention Prompt Learning Paradigm (TCPLP). Specifically, we capture semantic meanings by representing items through text rather than IDs, leveraging natural language universality to facilitate cross-domain knowledge transfer. Unlike prior works that need to conduct domain alignment, we directly learn transferable domain information, where two types of prompts, i.e., domain-shared and domain-specific prompts, are devised, with a co-attention-based network for prompt encoding. Then, we develop a two-stage learning strategy, i.e., pre-train & prompt-tuning paradigm, for domain knowledge pre-learning and transferring, respectively. We conduct extensive experiments on three datasets and the experimental results demonstrate the superiority of our TCPLP. Our source codes have been publicly released.
暂无评论