Relation-Oriented: Toward Causal Knowledge-Aligned AGI

TMLR Paper1448 Authors

Abstract:

Observation-Oriented paradigm currently dominates relationship learning models, including AI-based ones, which inherently do not account for relationships with temporally nonlinear effects.
Instead, this paradigm simplifies the ``temporal dimension'' as a linear observational timeline, necessitating the prior identification of effects with specific timestamps. Such constraints lead to \emph{identifiability difficulties} for dynamical effects, thereby overlooking the potentially crucial temporal nonlinearity of the modeled relationship.
Moreover, the multi-dimensional nature of Temporal Feature Space is largely disregarded, introducing inherent biases that seriously compromise the robustness and generalizability of relationship models. This limitation is particularly pronounced in large AI-based causal applications.

Examining these issues through the lens of a \emph{dimensionality framework}, a fundamental misalignment is identified between our relation-indexing comprehension of knowledge and the current modeling paradigm. To address this, a new Relation-Oriented paradigm is raised, aimed at facilitating the development of causal knowledge-aligned Artificial General Intelligence (AGI). As its methodological counterpart, the proposed Relation-Indexed Representation Learning (RIRL) is validated through efficacy experiments.

Submission Length: Long submission (more than 12 pages of main content)

Changes Since Last Submission:

Dear Reviewers and Editors,

This paper exists in THREE main versions:
1. the original, which spans approximately 25 pages, and
2. a revised version, comprising 20 pages, submitted on September 14th, Thursday. All subsequent revisions have been minor and focus on enhancing the presentation of the revised version.

%-----------------------%

3. The final version was uploaded on October 14th.
(A minor refinement is updated on October 17th/22nd/23rd.) \
I've streamlined the content, removing all complex metaphysical descriptions, observations, and analogies, and focused solely on computer science language.
If any part of the manuscript appears unclear or contains potentially inappropriate claims, please pinpoint the location, and I'll make the necessary adjustments.

I sincerely appreciate the timely response from the Chief on October 23rd. \
And I eagerly await your feedback and decision.

Best Regards

Assigned Action Editor: ~antonio_vergari2

Submission Number: 1448