- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Structural Abstraction, a framework for jointly learning neural predicates, reusable substructures, and formation rules from noisy perceptual demonstrations. The method combines variational predicate discovery, structural consistency search over contiguous subsequences, constrained grammar induction, and iterative representation refinement through abductive reasoning. Experiments on oracle-bone characters, modern Chinese characters, unseen radicals, and controlled digit sequences demonstrate substantially higher substructure discovery recall (SDR) than three feature-based motif-discovery baselines, along with generalization to unseen characters and radicals.
Critical strengths
- Valuable problem formulation. Unlike conventional neural-symbolic approaches that assume a predefined symbolic vocabulary, this work treats predicate identities, part boundaries, and compositional rules as joint learning targets. This formulation highlights an important challenge in learning the interface between neural perception and symbolic reasoning.
- Reasonable integration of perceptual and structural learning. The iterative framework allows structural consistency and induced rules to refine perceptual predicate assignments, while improved predicate representations facilitate the discovery of recurring substructures. Experiments on oracle-bone characters, modern Chinese characters, and controlled digit sequences provide complementary evidence across noisy real-world observations and settings with verifiable underlying grammars.
Critical weaknesses
- Limited evaluation of substructure discovery quality. The primary metric is macro-averaged recall over annotated substructures, which does not adequately assess false discoveries or the complexity of the induced symbolic theory. Since the method may generate numerous candidate substructures, reporting recall alone could overestimate discovery quality without complementary precision-oriented metrics or analysis of the learned theory size.
- Heavy reliance on predefined assumptions and hyperparameters. The framework depends on several manually specified components, including similarity thresholds, initial numbers of candidate symbols, pre-segmented strokes, known stroke orders, predefined relation types, a fixed abstraction hierarchy, and grammar induction templates. These assumptions substantially constrain the search space and raise concerns about the method's generalizability to less structured perceptual data, where such prior knowledge may not be readily available.
Questions for authors
Please refer to Weaknesses.
Author Rebuttal to Reviewer mqeY
We thank the reviewer for recognising the problem formulation and the interaction between perceptual and structural learning. We address discovery quality and prior assumptions below.
Precision and theory complexity
Response: We thank the reviewer for pointing out this evaluation gap. We agree that recall alone does not assess false discoveries. We have therefore added precision measurements:
These results complement SDR. We describe the measure as annotation precision because expert annotations are incomplete. For example, the radical “足” contains the structure “口”, but this nested component is absent from the annotations. An unmatched part may therefore be meaningful despite being counted as a false discovery under the annotation scheme. We will clarify the precision calculation and its limitations.
We also report the learned predicate counts, rule counts and part occurrences from the existing runs:
These counts describe the size of the learned theory. They include abstractions beyond the annotated radicals. Additional symbols and rules may also accommodate perceptual noise, as illustrated by the learned digit grammar. We will clarify the counting conventions and relate these statistics to the theory-size penalty in Eq. 1.
Sequential assumptions
Response: We thank the reviewer for raising this concern. We suggest that segmented atomic observations are common, for example in imitation learning and human's everyday teaching.
For example, a higher-order task decomposition of making coffee involves
grinding beans, heating water and brewing. However, for a learner, a demonstration may record only sensory observations and low-level actions, such as visual inputs and muscle movements. Hence, each transition xt=(st,at,st+1) is such an atomic observation. Its temporal position is given, but the learner is not told which transitions belong to what high-level behaviour or how the behaviours compose. Given a fragment of an ordered raw trace,a high-level symbolic description might be a grammar for example a regular expression A1+A2+A3+…. However, the symbols and their grounding must be learned:
This motivates our setting, and the abstraction is exactly the target of interface learning.
About hyperparameters
Response: We thank the reviewer for raising this concern. Most hyperparameters were chosen heuristically, with limited tuning. We agree that studying their effect on performance is valuable. Sensitivity experiments are running, and we will report their results in the revised paper.