Structured Relational Representations
Arun Kumar, Paul Schrater

TL;DR
This paper proposes a formal framework for structured relational invariant representations in learning systems, emphasizing the importance of partitions in an abstract knowledge space for stable and transferable knowledge.
Contribution
It introduces a novel formalization of invariant representations as partitions defined by relational paths within an abstract knowledge space, grounded in relational algebra.
Findings
Invariant partitions serve as the core of structured knowledge representations.
Relational algebra provides a formal foundation for these invariant structures.
Partitions enable stable, transferable knowledge in learning systems.
Abstract
Invariant representations are core to representation learning, yet a central challenge remains: uncovering invariants that are stable and transferable without suppressing task-relevant signals. This raises fundamental questions, requiring further inquiry, about the appropriate level of abstraction at which such invariants should be defined and which aspects of a system they should characterize. Interpretation of the environment relies on abstract knowledge structures to make sense of the current state, which leads to interactions, essential drivers of learning and knowledge acquisition. Interpretation operates at the level of higher-order relational knowledge; hence, we propose that invariant structures must be where knowledge resides, specifically as partitions defined by the closure of relational paths within an abstract knowledge space. These partitions serve as the core invariant…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
