The Structure-Mapping Engine: Algorithm and Examples

By Brian Falkenhainer, Kenneth D. Forbus, Dedre Gentner. 1989

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “(Clement, 1988; Eliot, 1986; Falkenhainer, Forbus, and Gentner, 1989; Forbus, Gentner, and Law, 1995; Gentner, Holyoak, and Kokinov, 2001; Hoffman, 1995; Spiro, Feltovich, Coulson, and Anderson, 1988)”
An Integrated Systems Approach to Explanation-Based Conceptual Change (2010, methodology): “Given two structured relational representations, SME computes one or two mappings which represent how they can be aligned.”
A symbolic-connectionist theory of relational inference and generalization. (2003, methodology): “Models such as SME (Falkenhainer et al., 1989) and IAM (Keane & Brayshaw, 1988) compute strict one-to-one mappings; indeed, without this hard constraint, their mapping algorithms would catastrophically fail.”
TODTLER: Two-Order-Deep Transfer Learning (2015, background): “The field of analogical reasoning (Falkenhainer, Forbus, and Gentner 1989) is also closely related to transfer learning.”
Mapping and Revising Markov Logic Networks for Transfer Learning (2007, methodology): “Similar predicate mappings are produced by analogy systems such as the Structure Mapping Engine (SME) ( Falkenhainer, Forbus, & Gentner 1989 ).”
The Oxford Handbook of Cognitive Psychology (2013, methodology): “The structure-mapping process has been formalized in a computer model called the Structure-Mapping Engine (SME; Falkenhainer et al., 1989).”
A Naturalistic Exploration of Forms and Functions of Analogizing (2009, methodology): “…must include criteria for when to reject candidate analogies due to explanatory breakdown, some sort of justification or evaluation processes (Falkenhainer et al., 1990; Kedar-Cabelli, 1988; Winston, 1979), and some process of special “radical restructuring” (Chalmers et al., 1992; Fass &…”
Comparison Facilitates Children's Learning of Names for Parts (2007, unknown): “exemplars that share relational structure but are dissimilar on the surface (Kotovsky & Gentner, 1996; Gentner & Namy, 1999; Loewenstein & Gentner, 2001; Namy & Gentner, 2002). This finding adds to evidence that comparison promotes the salience of connected relational systems over other commonalitie”
Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling (2019, background): “, structural similarities derived from works like [36]) lead to more efficiency with better performance.”
Darwin's mistake: Explaining the discontinuity between human and nonhuman minds (2008, unknown): “Information about one domain that is connected to the relational match can be carried over to the other domain as an analogical inference (Falkenhainer et al. 1989; Markman 1997; Spellman & Holyoak 1996).”