基于邻节点和关系模型优化的网络表示学习

网络表示学习旨在于将网络的拓扑结构、节点内容和其他信息嵌入到低维度的向量空间中,从而为网络数据挖掘、链路预测和推荐系统提供一种有效的工具.然而,现有的基于神经网络的表示学习算法即忽略了上下文节点的位置信息,又忽略了节点与文本之间的语义关联.因此,基于以上2点,提出了一种新颖的基于邻节点和关系模型优化的网络表示学习算法(network representation learning algorithm using the optimizations of neighboring vertices and relation model, NRNR).首先,该算法首次采用当前节点的邻居节点优化网络表示学习模型,使得上下文窗口中节点的位置信息被嵌入到网络表示中;其次,该算法首次引入知识表示学习中的关系模型建模节点之间的结构特征,使得节点之间的文本内容以关系约束的形式嵌入到网络表示中;再次,NRNR提出了一种可行且有效的网络表示联合学习框架,将上述2种目标融入到一个统一的优化目标函数中.实验结果表明：NRNR算法在网络节点分类任务中优于各类对比算法,在网络可视化中,NRNR算法学习得到的网络表示展现出了明显的聚类边界.     

综述：知识系统的V＆V技术

知识库的异常是影响整个知识系统性能的重要因素之一,因此必须对获取的知识进行校验。本文综述了知识库异常检测和验证的相关研究,给出了异常知识的分类及其危害性,分析了知识库验证困难的原因,介绍了用于知识库验证的静态和动态方法,列举了国际上几个著名的知识库验证工具,并对知识库验证的研究进行了展望。     

基于知识表示学习的实时语义数据流推理

传统的语义数据流推理使用前向或后向链式推理产生确定性的答案,但是在复杂的传递规则推理中效率不高,无法满足实时数据流处理场景对答案的及时性要求。因此,提出一种基于联合嵌入模型的知识表示方法,并应用于语义数据流处理中。将规则与事实三元组联合嵌入并利用深度学习模型进行训练,在推理阶段,根据查询中涉及的规则建立推理模板,利用深度学习模型对推理模板产生的三元组进行预测和分类,将结果作为查询和推理答案输出。实验表明,对于复杂规则推理,基于知识表示学习的实时语义数据流推理能够在保障较好推理准确性和命中率的前提下有效地降低延迟。     

A new process knowledge representation approach using parameter flow chart

Knowledge in various stages of the product development process has become increasingly important for manufacturing companies to improve their performance, especially for those One-of-a-Kind Production (OKP) companies producing highly customized products. Process knowledge is a very special type of knowledge that controls how products are best manufactured. This knowledge can help OKP companies produce high value-added products with better quality at shorter times and at a competitive cost. Process knowledge is normally hard to capture and manage and is even more difficult to represent. This paper proposes a Parameter Flow Chart (PFC) based new knowledge representation method which efficiently combines parameter information, flow chart technology, and visualization technology. The goal of this research is to provide a user-friendly and effective way of representing process knowledge for OKP companies so they can develop and accumulate their own process knowledge repository. The basic definition and principle of the approach will be introduced first and the software system model then proposed. Two related key issues, the modeling of various chart units used in the PFC approach and dealing with expressions containing various parameters, are discussed in detail. The prototype version of the system has been developed and demonstrated with case studies, which has proven the feasibility of the proposed approach.     

网络表示学习的研究与发展

网络表示学习旨在将网络中的节点表示成低维稠密且具有一定推理能力的向量,以运用于节点分类、社区发现和链路预测等社交网络应用任务中,是连接网络原始数据和网络应用任务的桥梁。传统的网络表示学习方法都是针对网络中节点和连边只有一种类型的同质信息网络的表示学习方法,而现实世界中的网络往往是具有多种节点和连边类型的异质信息网络。而且,从时间维度上来看,网络是不断变化的。因此,网络表示学习的研究方法随着网络数据的复杂化而不断变化。对近年来针对不同网络的网络表示学习方法进行了分类介绍,并阐述了网络表示学习的应用场景。     

Temporal Defeasible Reasoning

An argumentation system that allows temporal reasoning using the notions of instant and interval is presented. Previous proposals just considered either instants or intervals. A many-sorted logic is used to represent temporal knowledge at the monotonic level. The logic considers how to formalize knowledge about explicit temporal references, events, properties and actions. The argumentation system provides a non-monotonic layer in which to reason about the justification of truths in the system. The proposal is illustrated showing how to solve well-known problems of the literature. Received 21 June 2000 / Revised 7 December 2000 / Accepted in revised form 8 January 2001     

An investigation into knowledge-based yard crane scheduling for container terminals

To resolve the problems of operational efficiency, energy consumption and operational cost of an entire container terminal, the yard crane scheduling secures a crucial position during terminal operational process. Accordingly, it is imperative to develop an efficient yard crane scheduling strategy. In this study, the knowledge acquisition was initially conducted. Subsequently, a knowledge sorting process, including the taxonomic tree generation and organization of acquired knowledge, was completed. Afterwards, the rules were extracted for the purpose of yard crane scheduling. Furthermore, a mechanism was deployed for knowledge reasoning. Consequently, a knowledge-based system was established with regard to yard crane scheduling. To this end, a case study was used to illustrate the proposed knowledge-based system.     

基于自编码器的多视图属性网络表示学习模型

现有的大多数网络表示学习方法很难兼顾网络中丰富的结构信息和属性信息,导致其后续任务,如分类、聚类等的效果不佳.针对此问题,提出一种基于自编码器的多视图属性网络表示学习模型(AE-MVANR).首先,将网络的拓扑结构信息转化为拓扑结构视图(TSV),通过计算节点间相同属性共现频率来构造属性结构视图(ASV);然后,在两个...     

层次链专家系统方法在工资审批中的应用

文章介绍了将层次链专家系统方法应用于工资审批系统中工资审批计算过程,给出了层次链知识建模、知识表示的基本构架,描述了对属性、产生式规则和基于案例的推理流程,解决了工资计算的复杂性、多变性以及扩充性问题。     

集成时空轨迹的动态属性网络表征学习

网络表征学习是当前信息网络数据表示的研究热点,相比于传统网络分析技术已显示出它的有效性和高效性.目前绝大多数研究仅将网络视为静态来处理,即网络结构不随时间演化而变化,而且很少考虑网络中丰富的节点属性信息,难以适应现实信息网络时刻变化的动态特性.同时考虑网络的动态性和节点属性,提出基于时空路径的动态属性网络表征学习(DA...     

基于符号语义映射的知识图谱表示学习算法

图的分布式表示对于知识图谱的构建与应用任务至关重要.通过对当前流行的图表示学习模型进行比较,分析了现有模型存在的不合理之处,据此提出了一个基于符号语义映射的神经网络模型用于学习图的分布式表示,基本思想是依据知识图谱中已有的实体关系数据,采用循环神经网络对符号组合(实体-关系组合)进行语义编码,并将其映射到目标符号(实体)上.此外,通过为图中的每个关系类型引入一个逆关系镜像,解决了关系的非对称性问题,使模型能够适应多种不同类型的(同构或异构)网络的关系推理任务.该模型适用于大规模知识图谱的表示学习任务.在公开数据集上的实验结果表明,该模型在知识图谱扩容任务和基于图的多标签分类任务上的性能表现优于相关工作.     

On a rule-based interpretation of default conditionals

In nonmonotonic reasoning, a default conditional α→β has most often been informally interpreted as a defeasible version of a classical conditional, usually the material conditional. There is however an alternative interpretation, in which a default is regarded essentially as a rule, leading from premises to conclusion. In this paper, we present a family of logics, based on this alternative interpretation. A general semantic framework under this rule-based interpretation is developed, and associated proof theories for a family of weak conditional logics is specified. Nonmonotonic inference is easily defined in these logics. Interestingly, the logics presented here are weaker than the commonly-accepted base conditional approach for defeasible reasoning. However, this approach resolves problems that have been associated with previous approaches.      

From case-based reasoning to traces-based reasoning

CBR is an original AI paradigm based on the adaptation of solutions of past problems in order to solve new similar problems. Hence, a case is a problem with its solution and cases are stored in a case library. The reasoning process follows a cycle that facilitates “learning” from new solved cases. This approach can be also viewed as a lazy learning method when applied for task classification. CBR is applied for various tasks as design, planning, diagnosis, information retrieval, etc. The paper is the occasion to go a step further in reusing past unstructured experience, by considering traces of computer use as experience knowledge containers for situation based problem solving.     

社交网络中基于IAUE模型的锚链识别

社交网络中的锚链识别对于跨网络信息传播、跨平台推荐、社交链预测等具有重要意义.针对当前锚链识别研究中准确率低的问题,提出了一种有效提高锚链识别准确率的方法：IAUE模型.该模型首先利用网络结构信息进行网络表征学习,然后利用BP神经网络、随机梯度下降和负采样等方法得到异构网络节点间的锚链候选集,最后辅以G-S算法精化锚链匹配结果,提高异构网络对齐的准确率.多个数据集上的实验结果表明,IAUE方法相比其他方法具有较高的性能和很好的泛化能力,可以较为准确地识别网络中的锚链.     

Bayesian network modelling through qualitative patterns

In designing a Bayesian network for an actual problem, developers need to bridge the gap between the mathematical abstractions offered by the Bayesian-network formalism and the features of the problem to be modelled. Qualitative probabilistic networks (QPNs) have been put forward as qualitative analogues to Bayesian networks, and allow modelling interactions in terms of qualitative signs. They thus have the advantage that developers can abstract from the numerical detail, and therefore the gap may not be as wide as for their quantitative counterparts. A notion that has been suggested in the literature to facilitate Bayesian-network development is causal independence. It allows exploiting compact representations of probabilistic interactions among variables in a network. In the paper, we deploy both causal independence and QPNs in developing and analysing a collection of qualitative, causal interaction patterns, called QC patterns. These are endowed with a fixed qualitative semantics, and are intended to offer developers a high-level starting point when developing Bayesian networks.     

复杂网络的双曲空间表征学习方法

复杂网络在现实场景中无处不在,高效的复杂网络分析技术具有广泛的应用价值,比如社区检测、链路预测等.然而,很多复杂网络分析方法在处理大规模网络时需要较高的时间、空间复杂度.网络表征学习是一种解决该问题的有效方法,该类方法将高维稀疏的网络信息转化为低维稠密的实值向量,可以作为机器学习算法的输入,便于后续应用的高效计算.传统...     

A framework for knowledge-based temporal abstraction

A new domain-independent knowledge-based inference structure is presented, specific to the task of abstracting higher-level concepts from time-stamped data. The framework includes a model of time, parameters, events and contexts. A formal specification of a domain's temporal abstraction knowledge supports acquisition, maintenance, reuse and sharing of that knowledge.

The knowledge-based temporal abstraction method decomposes the temporal abstraction task into five subtasks. These subtasks are solved by five domain-independent temporal abstraction mechanisms. The temporal abstraction mechanisms depend on four domain-specific knowledge types: structural, classification (functional), temporal semantic (logical) and temporal dynamic (probabilistic) knowledge. Domain values for all knowledge types are specified when a temporal abstraction system is developed.

The knowledge-based temporal abstraction method has been implemented in the RÉSUMÉ system and has been evaluated in several clinical domains (protocol-based care, monitoring of children's growth and therapy of diabetes) and in an engineering domain (monitoring of traffic control), with encouraging results.