mlsanityData to 14 Oct 2026

TLINet: Differentiable Neural Network Temporal Logic Inference

arXiv 2405.06670 ↗First posted 3 May 2024cs.LO cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

There has been a growing interest in extracting formal descriptions of the system behaviors from data. Signal Temporal Logic (STL) is an expressive formal language used to describe spatial-temporal properties with interpretability. This paper introduces TLINet, a neural-symbolic framework for learning STL formulas. The computation in TLINet is differentiable, enabling the usage of off-the-shelf gradient-based tools during the learning process. In contrast to existing approaches, we introduce approximation methods for max operator designed specifically for temporal logic-based gradient techniques, ensuring the correctness of STL satisfaction evaluation. Our framework not only learns the structure but also the parameters of STL formulas, allowing flexible combinations of operators and various logical structures. We validate TLINet against state-of-the-art baselines, demonstrating that our approach outperforms these baselines in terms of interpretability, compactness, rich expressibility, and computational efficiency.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 15 of its 40 references that are in the map. First posted on arXiv 3 May 2024.

Builds on

15 of 40 references.

References · 15

  1. 2017Attention Is All You Needcited by 60,361
  2. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  3. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  4. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
  5. 2016Training Sparse Neural Networkscited by 73
  6. 2020Backpropagation through Signal Temporal Logic Specifications: Infusing Logical Structure into Gradient-Based Methodscited by 54
  7. 2020On Robustness Metrics for Learning STL Taskscited by 27
  8. 2020Specifying User Preferences using Weighted Signal Temporal Logiccited by 22
  9. 2019Interpretable Classification of Time-Series Data using Efficient Enumerative Techniquescited by 20
  10. 2018Information-Guided Temporal Logic Inference with Prior Knowledgecited by 13
  11. 2022Learning Signal Temporal Logic through Neural Network for Interpretable Classificationcited by 10
  12. 2021Classification of Time-Series Data Using Boosted Decision Treescited by 9
3 more
  1. 2021Weighted Graph-Based Signal Temporal Logic Inference Using Neural Networkscited by 5
  2. 2022Interpretable Fault Diagnosis of Rolling Element Bearings with Temporal Logic Neural Networkcited by 4
  3. 2024Interpretable Imitation Learning via Generative Adversarial STL Inference and Controlcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2025Conformal Prediction for Signal Temporal Logic Inferencecited by 3
  2. 2025Towards Interpretable Concept Learning over Time Series via Temporal Logic Semanticscited by 1
  3. 2025GradSTL: Comprehensive Signal Temporal Logic for Neurosymbolic Reasoning and Learningcited by 1
  4. 2026Conformalized Signal Temporal Logic Inference under Covariate Shiftcited by 1
  5. 2026First-Order Temporal Logic Tensor Networkscited by 1
  6. 2026SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specificationscited by 1
  7. 2025Guided by Stars: Interpretable Concept Learning Over Time Series via Temporal Logic Semanticscited by 0
  8. 2026Ask for Any Appliance: A Prompt-Programmable Foundation Model for Non-Intrusive Load Monitoringcited by 0
  9. 2026Class-Conditional Conformal Prediction for Signal Temporal Logic Inference with Many Classescited by 0