We address the problem of learning human-interpretable descriptions of a complex system from a finite set of positive and negative examples of its behavior. In contrast to most of the recent work in this area, which focuses on descriptions expressed in Linear Temporal Logic (LTL), we develop a learning algorithm for formulas in the IEEE standard temporal logic PSL (Property Specification Language). Our work is motivated by the fact that many natural properties, such as an event happening at every n-th point in time, cannot be expressed in LTL, whereas it is easy to express such properties in PSL. Moreover, formulas in PSL can be more succinct and easier to interpret (due to the use of regular expressions in PSL formulas) than formulas in LTL.
Our learning algorithm builds on top of an existing algorithm for learning LTL formulas. Roughly speaking, our algorithm reduces the learning task to a constraint satisfaction problem in propositional logic and then uses a SAT solver to search for a solution in an incremental fashion. We have implemented our algorithm and performed a comparative study between the proposed method and the existing LTL learning algorithm. Our results illustrate the effectiveness of the proposed approach to provide succinct human-interpretable descriptions from examples.
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
We consider the problem of combining machine learning models to perform higher-level cognitive tasks with clear specifications. We propose the novel problem of Visual Discrimination Puzzles (VDP) that requires finding interpretable discriminators that classify images according to a logical specification. Humans can solve these puzzles with ease and they give robust, verifiable, and interpretable discriminators as answers. We propose a compositional neurosymbolic framework that combines a neural network to detect objects and relationships with a symbolic learner that finds interpretable discrim…
Drug discovery aims to find novel compounds with specified chemical property profiles. In terms of generative modeling, the goal is to learn to sample molecules in the intersection of multiple property constraints. This task becomes increasingly challenging when there are many property constraints. We propose to offset this complexity by composing molecules from a vocabulary of substructures that we call molecular rationales. These rationales are identified from molecules as substructures that are likely responsible for each property of interest. We then learn to expand rationales into a full …
The performance of an organic photovoltaic device is intricately connected to its active layer morphology. This connection between the active layer and device performance is very expensive to evaluate, either experimentally or computationally. Hence, designing morphologies to achieve higher performances is non-trivial and often intractable. To solve this, we first introduce a deep convolutional neural network (CNN) architecture that can serve as a fast and robust surrogate for the complex structure-property map. Several tests were performed to gain trust in this trained model. Then, we utilize…
SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The 63rd Research Institute, National University of Defense Technology, Nanjing（国防科技大学第六三研究所，南京）
Brigham Young University（杨百翰大学）；University of Southern California（南加利福尼亚大学）
It is notoriously difficult to control the behavior of reinforcement learning agents. Agents often learn to exploit the environment or reward signal and need to be retrained multiple times. The multi-objective reinforcement learning (MORL) framework separates a reward function into several objectives. An ideal MORL agent learns to generalize to novel combinations of objectives allowing for better control of an agent's behavior without requiring retraining. Many MORL approaches use a weight vector to parameterize the importance of each objective. However, this approach suffers from lack of expr…
Extracting human interpretable structure-property relationships in chemistry using XAI and large language models
Laboratory of Artificial Chemical Intelligence（人工智能化学智能实验室）；Institute of Chemical Sciences and Engineering（化学科学与工程研究所）；Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
Functional Groups are All you Need for Chemically Interpretable Molecular Property Prediction
BioSystems Engineering and Control Lab（生物系统工程与控制实验室）；Indian Institute of Technology Madras（印度理工学院马德拉斯学院）；Wadhwani School of Data Science and AI（瓦德哈尼数据科学与人工智能学校）；Indian Institute of Technology Madras Zanzibar（印度理工学院马德拉斯扎辛巴尔）
A General Framework for Property-Driven Machine Learning
Maynooth University（梅诺特大学）；Heriot-Watt University（赫瑞-瓦特大学）；University of Edinburgh（爱丁堡大学）；Edinburgh Centre for Robotics（爱丁堡机器人中心）；University of Southampton（南安普顿大学）
Interpretable Ensemble Learning for Materials Property Prediction with Classical Interatomic Potentials: Carbon as an Example
School for Engineering of Matter, Transport and Energy, Arizona State University（亚利桑那州立大学物质、运输与能源工程学院）；Material Measurement Laboratory, National Institute of Standards and Technology（美国国家标准与技术研究院材料测量实验室）
GeoT: A Geometry-aware Transformer for Reliable Molecular Property Prediction and Chemically Interpretable Representation Learning
Kakao Corporation（Kakao公司）；LG Chem（LG化学）；Seoul National University（首尔国立大学）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））；Seoul National University of Science and Technology（首尔国立科技大学）
Modern approaches to building interpretable models of the property market using machine learning on the base of mass cadastral valuation
Beijing Institute of Mathematical Sciences and Applications（北京数学科学研究院）；Independent Researcher（独立研究者）；Center of cadastral valuation for Primorsky Krai（普里莫尔边疆区土地评估中心）
In this paper we propose a novel human-centered approach for detecting forgery in face images, using dynamic prototypes as a form of visual explanations. Currently, most state-of-the-art deepfake detections are based on black-box models that process videos frame-by-frame for inference, and few closely examine their temporal inconsistencies. However, the existence of such temporal artifacts within deepfake videos is key in detecting and explaining deepfakes to a supervising human. To this end, we propose Dynamic Prototype Network (DPNet) -- an interpretable and effective solution that utilizes …
Auto-ADMET: An Effective and Interpretable AutoML Method for Chemical ADMET Property Prediction
Baker Heart and Diabetes Institute（贝克心脏与糖尿病研究所）；School of Chemistry & Molecular Biosciences, The University of Queensland（昆士兰大学化学与分子生物科学学院）；Department of Cardiometabolic Health, The University of Melbourne（墨尔本大学心脏代谢健康系）
Interpretable Machine Learning for Quantum-Informed Property Predictions in Artificial Sensing Materials
Institute for Materials Science（材料科学研究所）；Max Bergmann Center for Biomaterials（生物材料中心）；TUD Dresden University of Technology（德累斯顿技术大学）；Institute of Physical Chemistry（物理化学研究所）；Friedrich Schiller University Jena（耶拿弗里德里希·施莱尔大学）；Dresden Center for Computational Materials Science (DCMS)（德累斯顿计算材料科学中心）；Cluster of Excellence CARE（卓越中心CARE）；Cluster of Excellence CeTI（卓越中心CeTI）
Explaining black-box Artificial Intelligence (AI) models is a cornerstone for trustworthy AI and a prerequisite for its use in safety critical applications such that AI models can reliably assist humans in critical decisions. However, instead of trying to explain our models post-hoc, we need models which are interpretable-by-design built on a reasoning process similar to humans that exploits meaningful high-level concepts such as shapes, texture or object parts. Learning such concepts is often hindered by its need for explicit specification and annotation up front. Instead, prototype-based lea…
