Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Deductive Reasoning01:16

Deductive Reasoning

62.8K
Deductive reasoning, or deduction, is the type of logic used in hypothesis-based science. In deductive reasoning, the pattern of thinking moves in the opposite direction as compared to inductive reasoning, which means that it uses a general principle or law to predict specific results. From those general principles, a scientist can deduce and predict the specific results that would be valid as long as the general principles are valid.
For example, a researcher can deduce specific predictions...
62.8K
Inductive Reasoning00:59

Inductive Reasoning

63.7K
Inductive reasoning is a form of logical thinking that uses related observations to arrive at a general conclusion. It is uncertain and operates in degrees to which the conclusions are credible. As such, inductive arguments can be weak or strong, rather than valid or invalid, and conclusions can be used to formulate testable, falsifiable hypotheses.
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
63.7K
Reasoning01:30

Reasoning

205
Reasoning is the action of thinking about something in a logical, sensible way. It is integral to problem-solving, decision-making, and critical thinking. Reasoning can be inductive or deductive. Reasoning involves transforming information into conclusions, which is essential for problem-solving, decision-making, and critical thinking.
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
205
Schemas01:42

Schemas

12.1K
A schema is a mental construct consisting of a cluster or collection of related concepts (Bartlett, 1932). There are many different types of schemata, and they all have one thing in common: schemata are a method of organizing information that allows the brain to work more efficiently. When a schema is activated, the brain makes immediate assumptions about the person or object being observed.
12.1K
Reason and Intuition01:37

Reason and Intuition

7.1K
The human brain processes information for decision-making using one of two routes: an intuitive system and a rational system (Epstein, 1994; popularized by Kahneman, 2011 as System 1 and System 2, respectively). The intuitive system is quick, impulsive, and operates with minimal effort, relying on emotions or habits to provide cues for what to do next, while the rational system is logical, analytical, deliberate, and methodical. Research in neuropsychology suggests that the...
7.1K
Collisions in Multiple Dimensions: Problem Solving01:06

Collisions in Multiple Dimensions: Problem Solving

4.6K
In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
4.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Domain knowledge embedded anti-disturbance autonomous navigation for marine vehicles.

Communications engineering·2026
Same author

Oxygen-directed, copper-catalyzed, diastereoselective protosilylation of cyclopropenes.

Chemical communications (Cambridge, England)·2026
Same author

Amphiphilic xanthotoxin derivatives with phosphatidylglycerol-targeting membrane disruption for potent anti-methicillin-resistant Staphylococcus aureus (MRSA) activity.

European journal of medicinal chemistry·2026
Same author

Data-Driven Backstepping Control for a Class of Unknown Nonlinear Strict-Feedback Systems.

IEEE transactions on cybernetics·2025
Same author

Antioomycete Activity and Mechanism of Territrem B, against <i>Phytophthora capsici</i> in Prevention of <i>Phytophthora</i> Blight.

Journal of agricultural and food chemistry·2025
Same author

Copper-Catalyzed Stereoconvergent 1,4-Protosilylation of <i>E</i>/<i>Z</i> Dienes.

Organic letters·2025

Related Experiment Video

Updated: Nov 1, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

805

HiAM: A Hierarchical Attention based Model for knowledge graph multi-hop reasoning.

Ting Ma1, Shangwen Lv1, Longtao Huang2

  • 1University of Chinese Academy of Sciences, Beijing 100049, China; Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China.

Neural Networks : the Official Journal of the International Neural Network Society
|June 22, 2021
PubMed
Summary

This study introduces HiAM, a novel Hierarchical Attention based Model for knowledge graph multi-hop reasoning. HiAM improves reasoning accuracy by incorporating predecessor paths and hierarchical attention mechanisms.

Keywords:
Hierarchical AttentionKnowledge graph reasoningPredecessor paths

More Related Videos

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.9K

Related Experiment Videos

Last Updated: Nov 1, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

805
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.9K

Area of Science:

  • Artificial Intelligence
  • Computer Science
  • Data Science

Background:

  • Knowledge graph reasoning is crucial for AI applications like question answering.
  • Current methods for multi-hop reasoning in knowledge graphs have limitations in synthesizing path information.
  • Existing approaches overlook the significance of predecessor paths and uniform importance of entities/relations within paths.

Purpose of the Study:

  • To propose a novel model, HiAM (Hierarchical Attention based Model), for enhanced multi-hop reasoning in knowledge graphs.
  • To leverage predecessor paths for more accurate semantic representations.
  • To explore multi-granularity features for improved reasoning performance and provide path-based explanations.

Main Methods:

  • Extraction of predecessor paths for head entities and connection paths between entity pairs.
  • Design of a hierarchical attention mechanism to capture entity/relation-level and path-level features.
  • Fusion of multi-granularity features for answer prediction and selection of significant paths for explanation.

Main Results:

  • The proposed HiAM model demonstrates competitive performance against baseline methods on benchmark datasets.
  • Incorporating predecessor paths enhances semantic representations for knowledge graph reasoning.
  • Hierarchical attention effectively captures multi-granularity features, leading to improved reasoning outcomes.

Conclusions:

  • HiAM offers a significant advancement in knowledge graph multi-hop reasoning by utilizing predecessor paths and hierarchical attention.
  • The model's ability to provide explanations by selecting significant paths enhances interpretability.
  • The findings suggest that considering path hierarchies and varying entity/relation importance is key for effective knowledge graph reasoning.