A mathematical theory is presented for the representation of knowledge in the form of a directed acyclic hierarchy of objects in a category where all paths between any given pair of objects are required to be equal. The conditions under which knowledge update, in the form of the sesqui-pushout rewriting of an object in a hierarchy, can be propagated to the rest of the hierarchy, in order to maintain all required path equalities, are analysed: some rewrites must be propagated forwards, in the direction of the arrows, while others must be propagated backwards, against the direction of the arrows, and, depending on the precise form of the hierarchy, certain composability conditions may also be necessary. The implementation of this theory, in the ReGraph Python library for (simple) directed graphs with attributes on nodes and edges, is then discussed in the context of two significant use cases.
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；Technische Universität Wien（维也纳工业大学）
Dealing with context dependent knowledge has led to different formalizations of the notion of context. Among them is the Contextualized Knowledge Repository (CKR) framework, which is rooted in description logics but links on the reasoning side strongly to logic programs and Answer Set Programming (ASP) in particular. The CKR framework caters for reasoning with defeasible axioms and exceptions in contexts, which was extended to knowledge inheritance across contexts in a coverage (specificity) hierarchy. However, the approach supports only this single type of contextual relation and the reasonin…
University of Southern California（南加州大学）；University of California, Los Angeles（加州大学洛杉矶分校）
Recently there is an increasing scholarly interest in time-varying knowledge graphs, or temporal knowledge graphs (TKG). Previous research suggests diverse approaches to TKG reasoning that uses historical information. However, less attention has been given to the hierarchies within such information at different timestamps. Given that TKG is a sequence of knowledge graphs based on time, the chronology in the sequence derives hierarchies between the graphs. Furthermore, each knowledge graph has its hierarchical level which may differ from one another. To address these hierarchical characteristic…
Many systems have been developed in recent years to mine logical rules from large-scale Knowledge Graphs (KGs), on the grounds that representing regularities as rules enables both the interpretable inference of new facts, and the explanation of known facts. Among these systems, the walk-based methods that generate the instantiated rules containing constants by abstracting sampled paths in KGs demonstrate strong predictive performance and expressivity. However, due to the large volume of possible rules, these systems do not scale well where computational resources are often wasted on generating…
Institute for Robotics and Intelligent Machines（机器人与智能机器研究所）；Georgia Institute of Technology（佐治亚理工学院）
The objective of the knowledge base completion problem is to infer missing information from existing facts in a knowledge base. Prior work has demonstrated the effectiveness of path-ranking based methods, which solve the problem by discovering observable patterns in knowledge graphs, consisting of nodes representing entities and edges representing relations. However, these patterns either lack accuracy because they rely solely on relations or cannot easily generalize due to the direct use of specific entity information. We introduce Attentive Path Ranking, a novel path pattern representation t…
Method for the semantic indexing of concept hierarchies, uniform representation, use of relational database systems and generic and case-based reasoning
TU Dresden（德累斯顿工业大学）；Frauenhofer Institut für Intelligente Analyse und Informationssysteme IAIS（弗劳恩霍夫智能分析与信息系统研究所IAIS）
University of Genoa（热那亚大学）；Teseo s.r.l.（Teseo有限公司）
OWLOOP is an Application Programming Interface (API) for using the Ontology Web Language (OWL) by the means of Object-Oriented Programming (OOP). It is common to design software architectures using the OOP paradigm for increasing their modularity. If the components of an architecture also exploit OWL ontologies for knowledge representation and reasoning, they would require to be interfaced with OWL axioms. Since OWL does not adhere to the OOP paradigm, such an interface often leads to boilerplate code affecting modularity, and OWLOOP is designed to address this issue as well as the associated …
In this paper, we study how graph transformations based on sesqui-pushout rewriting can be reversed and how the composition of rewrites can be constructed. We illustrate how such reversibility and composition can be used to design an audit trail system for individual graphs and graph hierarchies. This provides us with a compact way to maintain the history of updates of an object, including its multiple versions. The main application of the designed framework is an audit trail of updates to knowledge represented by hierarchies of graphs. Therefore, we introduce the notion of rule hierarchy that…
University of Stuttgart（斯图加特大学）；University of Bonn（波恩大学）；Monash University（莫纳什大学）；University of Southampton（南安普顿大学）
Recent knowledge graph (KG) embeddings have been advanced by hyperbolic geometry due to its superior capability for representing hierarchies. The topological structures of real-world KGs, however, are rather heterogeneous, i.e., a KG is composed of multiple distinct hierarchies and non-hierarchical graph structures. Therefore, a homogeneous (either Euclidean or hyperbolic) geometry is not sufficient for fairly representing such heterogeneous structures. To capture the topological heterogeneity of KGs, we present an ultrahyperbolic KG embedding (UltraE) in an ultrahyperbolic (or pseudo-Riemanni…
Technische Universität Dresden（德累斯顿工业大学）；University of Wrocław（弗罗茨瓦夫大学）
In logic-based knowledge representation, query answering has essentially replaced mere satisfiability checking as the inferencing problem of primary interest. For knowledge bases in the basic description logic ALC, the computational complexity of conjunctive query (CQ) answering is well known to be ExpTime-complete and hence not harder than satisfiability. This does not change when the logic is extended by certain features (such as counting or role hierarchies), whereas adding others (inverses, nominals or transitivity together with role-hierarchies) turns CQ answering exponentially harder. We…
Data Science Institute（数据科学研究所）；Insight Centre for Data Analytics（洞察数据分析中心）；National University of Ireland Galway（爱尔兰国立高威大学）
Knowledge graphs have attracted lots of attention in academic and industrial environments. Despite their usefulness, popular knowledge graphs suffer from incompleteness of information, especially in their type assertions. This has encouraged research in the automatic discovery of entity types. In this context, multiple works were developed to utilize logical inference on ontologies and statistical machine learning methods to learn type assertion in knowledge graphs. However, these approaches suffer from limited performance on noisy data, limited scalability and the dependence on labeled traini…
The Artificial Intelligence Ontology: LLM-assisted construction of AI concept hierarchies
Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；UC Berkeley（加州大学伯克利分校）；Helen Wills Neuroscience Institute（海伦·威尔斯神经科学研究所）；Redwood Center for Theoretical Neuroscience（红杉理论神经科学中心）
Taxonomies are an important ingredient of knowledge organization, and serve as a backbone for more sophisticated knowledge representations in intelligent systems, such as formal ontologies. However, building taxonomies manually is a costly endeavor, and hence, automatic methods for taxonomy induction are a good alternative to build large-scale taxonomies. In this paper, we propose TIEmb, an approach for automatic unsupervised class subsumption axiom extraction from knowledge bases using entity and text embeddings. We apply the approach on the WebIsA database, a database of subsumption relation…
AstraZeneca（阿斯利康）；The University of Liverpool（利物浦大学）
Duplication of nodes is a common problem encountered when building knowledge graphs (KGs) from heterogeneous datasets, where it is crucial to be able to merge nodes having the same meaning. OntoMerger is a Python ontology integration library whose functionality is to deduplicate KG nodes. Our approach takes a set of KG nodes, mappings and disconnected hierarchies and generates a set of merged nodes together with a connected hierarchy. In addition, the library provides analytic and data testing functionalities that can be used to fine-tune the inputs, further reducing duplication, and to increa…
Hyperbolic Graph Representation Learning for Differential Diagnosis on Biomedical Knowledge Graphs
Università degli Studi di Milano（米兰大学）；Università della Svizzera italiana (USI)（瑞士意大利语大学）；Politecnico di Milano（米兰理工大学）；Aalto University（阿尔托大学）；FGV（杰图利奥·瓦加斯基金会）
Joint Supercomputer Center of the Russian Academy of Sciences（俄罗斯科学院联合超级计算机中心）；Kazan Federal University（喀山联邦大学）
This paper is devoted to the problems of ontology-based mathematical knowledge management and representation. The main attention is paid to the development of a formal model for the representation of mathematical statements in the Open Linked Data cloud. The proposed model is intended for applications that extract mathematical facts from natural language mathematical texts and represent these facts as Linked Open Data. The model is used in development of a new version of the OntoMath${}^{\mathrm{PRO}}$ ontology of professional mathematics is described. OntoMath${}^{\mathrm{PRO}}$ underlies a s…
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the low-resource translation by leveraging data from multiple languages. However, the performance of an MNMT model is highly dependent on the type of languages used in training, as transferring knowledge from a diverse set of languages degrades the translation performance due to negative transfer. In this paper, we propose a Hierarchical Knowledge Distillation (HKD) approa…
Hong Kong University of Science and Technology（香港科技大学）
A class or taxonomic hierarchy is often manually constructed, and part of our knowledge about the world. In this paper, we propose a novel algorithm for automatically acquiring a class hierarchy from a classifier which is often a large neural network these days. The information that we need from a classifier is its confusion matrix which contains, for each pair of base classes, the number of errors the classifier makes by mistaking one for another. Our algorithm produces surprisingly good hierarchies for some well-known deep neural network models trained on the CIFAR-10 dataset, a neural netwo…
University College London（伦敦大学学院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Accelex Technology（Accelex科技）
Multi-hop QA (Question Answering) is the task of finding the answer to a question across multiple documents. In recent years, a number of Deep Learning-based approaches have been proposed to tackle this complex task, as well as a few standard benchmarks to assess models Multi-hop QA capabilities. In this paper, we focus on the well-established HotpotQA benchmark dataset, which requires models to perform answer span extraction as well as support sentence prediction. We present two extensions to the SOTA Graph Neural Network (GNN) based model for HotpotQA, Hierarchical Graph Network (HGN): (i) w…
AIT Lab, Department of Computer Science, ETH Zurich（苏黎世联邦理工学院计算机科学系AIT实验室）
We present HiDe, a novel hierarchical reinforcement learning architecture that successfully solves long horizon control tasks and generalizes to unseen test scenarios. Functional decomposition between planning and low-level control is achieved by explicitly separating the state-action spaces across the hierarchy, which allows the integration of task-relevant knowledge per layer. We propose an RL-based planner to efficiently leverage the information in the planning layer of the hierarchy, while the control layer learns a goal-conditioned control policy. The hierarchy is trained jointly but allo…
Paul G. Allen School of Computer Science and Engineering（保罗·G·艾伦计算机科学与工程学院）；University of Washington, Seattle（华盛顿大学西雅图分校）
We introduce Active Predictive Coding Networks (APCNs), a new class of neural networks that solve a major problem posed by Hinton and others in the fields of artificial intelligence and brain modeling: how can neural networks learn intrinsic reference frames for objects and parse visual scenes into part-whole hierarchies by dynamically allocating nodes in a parse tree? APCNs address this problem by using a novel combination of ideas: (1) hypernetworks are used for dynamically generating recurrent neural networks that predict parts and their locations within intrinsic reference frames condition…
Diagnosing Retrieval Bias Under Multiple In-Context Knowledge Updates in Large Language Models
Institute of Information Engineering, Chinese Academy of Sciences（信息工程研究所，中国科学院）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络与安全学院）；Hong Kong University of Science and Technology（香港科学与技术大学）；The University of Manchester（曼彻斯特大学）
Optimizing Student Ability Assessment: A Hierarchy Constraint-Aware Cognitive Diagnosis Framework for Educational Contexts
University of Science and Technology of China（中国科学技术大学）；Liupanshui Normal University（六盘水师范学院）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；National University of Singapore（新加坡国立大学）
FedReview: Review and Dispose Poisoned Updates without Validation Datasets or Historic Knowledge
Zhejiang University（浙江大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新区（滨江）区块链与数据安全研究院）；ZJU-UIUC Institute, Zhejiang University（浙江大学ZJU-UIUC研究院）；University of Toronto（多伦多大学）
Data-Aware Model Merging in the Essential Subspace for Multi-Task Knowledge Aggregation
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其交叉应用国家重点实验室（东南大学））；Huawei Inc.（华为公司）
The open domain knowledge base is very important. It is usually extracted from encyclopedia websites and is widely used in knowledge retrieval systems, question answering systems, or recommendation systems. In practice, the key challenge is to maintain an up-to-date knowledge base. Different from Unwieldy fetching all of the data from the encyclopedia dumps, to enlarge the freshness of the knowledge base as big as possible while avoiding invalid fetching, the current knowledge base updating methods usually determine whether entities need to be updated by building a prediction model. However, t…
