Knowledge-Based Entity Prediction for Improved Machine Perception in Autonomous Systems

  title={Knowledge-Based Entity Prediction for Improved Machine Perception in Autonomous Systems},
  author={Ruwan Wickramarachchi and Cory Andrew Henson and A. Sheth},
  journal={IEEE Intelligent Systems},
Knowledge-based entity prediction (KEP) is a novel task that aims to improve machine perception in autonomous systems. KEP leverages relational knowledge from heterogeneous sources in predicting potentially unrecognized entities. In this article, we provide a formal definition of KEP as a knowledge completion task. Three potential solutions are then introduced, which employ several machine learning and data mining techniques. Finally, the applicability of KEP is demonstrated on two autonomous… 
1 Citations

Figures and Tables from this paper

A Semantic Web Approach to Fault Tolerant Autonomous Manufacturing

The next phase of manufacturing is centered on making the switch from traditional automated to autonomous systems. Future factories are required to be agile, allowing for more customized production



Knowledge-infused Learning for Entity Prediction in Driving Scenes

An innovative neuro-symbolic solution for KEP is presented, based on knowledge-infused learning, which introduces a dataset agnostic ontology to describe driving scenes, uses an expressive, holistic representation of scenes with knowledge graphs, and proposes an effective, non-standard mapping of the KEP problem to the problem of link prediction (LP) using knowledge-graph embeddings (KGE).

Towards Leveraging Commonsense Knowledge for Autonomous Driving

This work extends existing autonomous driving knowledge graphs with commonsense knowledge, and demonstrates empirically the benefits of such extension for two downstream applications: object prediction and explainable scene clustering.

An Evaluation of Knowledge Graph Embeddings for Autonomous Driving Data: Experience and Practice

Higher levels of informational detail in KGs lead to higher quality embeddings, type and relation semantics are better captured by the semantic transitional distance-based TransE algorithm, and some metrics, such as coherence measure, may not be suitable for intrinsically evaluating KGEs in this domain.

Knowledge Graph Embedding for Link Prediction: A Comparative Analysis

A comprehensive comparison of embedding-based LP methods is provided, extending the dimensions of analysis beyond what is commonly available in the literature, and experimentally compare effectiveness and efficiency of 16 state-of-the-art methods.

CSKG: The CommonSense Knowledge Graph

This paper shows the impact of CSKG as a source for reasoning evidence retrieval, and for pre-training language models for generalizable downstream reasoning, and applies five principles to combine seven key sources into a first integrated CommonSense Knowledge Graph (CSKG).

Knowledge Infusion

It is argued that robust logic offers an appropriate semantics for this endeavor because it supports provably efficient algorithms for a basic set of necessary learning and reasoning tasks.

A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network

The model ConvKB advances state-of-the-art models by employing a convolutional neural network, so that it can capture global relationships and transitional characteristics between entities and relations in knowledge bases.

Translating Embeddings for Modeling Multi-relational Data

TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.

Holographic Embeddings of Knowledge Graphs

Holographic embeddings (HolE) are proposed to learn compositional vector space representations of entire knowledge graphs to outperform state-of-the-art methods for link prediction on knowledge graphs and relational learning benchmark datasets.

Shades of Knowledge-Infused Learning for Enhancing Deep Learning

A continuum that comprises of three stages for infusion of knowledge into the machine/deep learning architectures is described, which starts with shallow infusion in the form of embeddings, and attention and knowledge-based constraints improve with a semideep infusion.