LAF-Based Evaluation and UTTL-Based Learning Strategies with MIATTs

2026-04-22

AI Summary

This work addresses the challenge in machine learning where ground-truth labels cannot be objectively defined due to ambiguous or subjective targets. Within the EL-MIATTs framework, it introduces a structured co-design mechanism that synergistically integrates logical semantics (LAF) with statistical optimization (UTTL). The proposed approach leverages LAF to handle raw or multi-valued composite targets and employs UTTL strategies—utilizing Dice and cross-entropy losses—to enable optimization at either the target or aggregate level. Crucially, this method achieves logically consistent and practically feasible training and evaluation without requiring explicit ground-truth labels. By moving beyond the conventional paradigm reliant on definite annotations, the study establishes a principled, interpretable, reliable, and theoretically complete modeling pathway for weakly supervised tasks characterized by label ambiguity.

Technology Category

Machine Learning: Statistical Relational/Logic LearningConstraint Satisfaction and Optimization: Satisfiability Modulo TheoriesReasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

In many real-world machine learning (ML) applications, the true target cannot be precisely defined due to ambiguity or subjectivity information. To address this challenge, under the assumption that the true target for a given ML task is not assumed to exist objectively in the real world, the EL-MIATTs (Evaluation and Learning with Multiple Inaccurate True Targets) framework has been proposed. Bridging theory and practice in implementing EL-MIATTs, in this paper, we develop two complementary mechanisms: LAF (Logical Assessment Formula)-based evaluation algorithms and UTTL (Undefinable True Target Learning)-based learning strategies with MIATTs, which together enable logically coherent and practically feasible modeling under uncertain supervision. We first analyze task-specific MIATTs, examining how their coverage and diversity determine their structural property and influence downstream evaluation and learning. Based on this understanding, we formulate LAF-grounded evaluation algorithms that operate either on original MIATTs or on ternary targets synthesized from them, balancing interpretability, soundness, and completeness. For model training, we introduce UTTL-grounded learning strategies using Dice and cross-entropy loss functions, comparing per-target and aggregated optimization schemes. We also discuss how the integration of LAF and UTTL bridges the gap between logical semantics and statistical optimization. Together, these components provide a coherent pathway for implementing EL-MIATTs, offering a principled foundation for developing ML systems in scenarios where the notion of "ground truth" is inherently uncertain. An application of this work's results is presented as part of the study available at https://www.qeios.com/read/EZWLSN.

Problem

• Uncertain Supervision
• Multiple Inaccurate True Targets
• Undefinable True Target
• Ambiguous Labels
• Subjective Ground Truth

Innovation

• LAF
• UTTL
• MIATTs
• uncertain supervision
• logical assessment