English
Related papers

Related papers: Provably Explaining Neural Additive Models

200 papers

We consider the dictionary learning problem, where the aim is to model the given data as a linear combination of a few columns of a matrix known as a dictionary, where the sparse weights forming the linear combination are known as…

Machine Learning · Computer Science 2019-08-29 Sirisha Rambhatla , Xingguo Li , Jarvis Haupt

Providing safety guarantees for autonomous systems is difficult as these systems operate in complex environments that require the use of learning-enabled components, such as deep neural networks (DNNs) for visual perception. DNNs are hard…

Artificial Intelligence · Computer Science 2023-05-31 Corina Pasareanu , Ravi Mangal , Divya Gopinath , Huafeng Yu

The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging interpretable-by-design methods, which aim to redesign ML algorithms for…

Machine Learning · Computer Science 2025-05-28 Geyu Liang , Senne Michielssen , Salar Fattahi

An important task for recommender system is to generate explanations according to a user's preferences. Most of the current methods for explainable recommendations use structured sentences to provide descriptions along with the…

Computation and Language · Computer Science 2017-07-07 Felipe Costa , Sixun Ouyang , Peter Dolog , Aonghus Lawlor

Continual learning can enable neural networks to evolve by learning new tasks sequentially in task-changing scenarios. However, two general and related challenges should be overcome in further research before we apply this technique to…

Machine Learning · Computer Science 2022-02-15 Yujiang He , Zhixin Huang , Bernhard Sick

The ability to deploy neural networks in real-world, safety-critical systems is severely limited by the presence of adversarial examples: slightly perturbed inputs that are misclassified by the network. In recent years, several techniques…

Machine Learning · Computer Science 2018-02-21 Nicholas Carlini , Guy Katz , Clark Barrett , David L. Dill

Advances in the effectiveness of machine learning models have come at the cost of enormous complexity resulting in a poor understanding of how they function. Local surrogate methods have been used to approximate the workings of these…

Machine Learning · Computer Science 2025-01-16 Christopher Burger , Charles Walter

We present a heuristic strategy for marginal MAP (MMAP) queries in graphical models. The algorithm is based on a reduction of the task to a polynomial number of marginal inference computations. Given an input evidence, the marginals mass…

Artificial Intelligence · Computer Science 2020-02-13 Alessandro Antonucci , Thomas Tiotto

Sequence models are a critical component of modern NLP systems, but their predictions are difficult to explain. We consider model explanations though rationales, subsets of context that can explain individual model predictions. We find…

Computation and Language · Computer Science 2021-11-19 Keyon Vafa , Yuntian Deng , David M. Blei , Alexander M. Rush

To construct interpretable explanations that are consistent with the original ML model, counterfactual examples---showing how the model's output changes with small perturbations to the input---have been proposed. This paper extends the work…

Machine Learning · Computer Science 2020-06-16 Divyat Mahajan , Chenhao Tan , Amit Sharma

The emergence of tools based on artificial intelligence has also led to the need of producing explanations which are understandable by a human being. In most approaches, the system is considered a black box, making it difficult to generate…

Artificial Intelligence · Computer Science 2024-10-23 Germán Vidal

Knowledge-augmented learning enables the combination of knowledge-based and data-driven approaches. For anomaly detection and diagnosis, understandability is typically an important factor, especially in high-risk areas. Therefore,…

Machine Learning · Computer Science 2024-12-03 Martin Atzmueller , Tim Bohne , Patricia Windler

Interpretability has become an essential topic for artificial intelligence in some high-risk domains such as healthcare, bank and security. For commonly-used tabular data, traditional methods trained end-to-end machine learning models with…

Artificial Intelligence · Computer Science 2022-08-18 Haixiao Chi , Dawei Wang , Gaojie Cui , Feng Mao , Beishui Liao

Mechanistic Interpretability aims to understand neural networks through causal explanations. We argue for the Explanatory View Hypothesis: that Mechanistic Interpretability research is a principled approach to understanding models because…

Machine Learning · Computer Science 2025-05-05 Kola Ayonrinde , Louis Jaburi

Identifying cause-effect relations among variables is a key step in the decision-making process. While causal inference requires randomized experiments, researchers and policymakers are increasingly using observational studies to test…

Optimization and Control · Mathematics 2021-11-22 Md Saiful Islam , Md Sarowar Morshed , Md. Noor-E-Alam

Neuro-Symbolic Artificial Intelligence (NeSy AI) has emerged as a promising direction for integrating neural learning with symbolic reasoning. Typically, in the probabilistic variant of such systems, a neural network first extracts a set of…

Large language models (LLMs) are increasingly explored for NP-hard combinatorial optimization problems, but most existing methods emphasize feasible-instance solution generation and do not explicitly address infeasibility detection. We…

Artificial Intelligence · Computer Science 2026-04-15 Yakun Wang , Min Chen , Zeguan Wu , Junyu Liu , Sitao Zhang , Zhenwen Shao

Answer Set Programming (ASP) is a logic-based knowledge representation framework, supporting---among other reasoning modes---the central task of query answering. In the propositional case, query answering amounts to computing cautious…

Logic in Computer Science · Computer Science 2018-04-24 Mario Alviano , Carmine Dodaro , Matti Järvisalo , Marco Maratea , Alessandro Previti

Deep neural networks (DNNs) have proven to be highly effective in a variety of tasks, making them the go-to method for problems requiring high-level predictive power. Despite this success, the inner workings of DNNs are often not…

Machine Learning · Statistics 2024-03-04 Anton Thielmann , René-Marcel Kruse , Thomas Kneib , Benjamin Säfken

Deep learning has become the dominant approach for creating high capacity, scalable models across diverse data modalities. However, because these models rely on a large number of learned parameters, tightly couple feature extraction with…

Artificial Intelligence · Computer Science 2026-05-12 Adam Gould , Francesca Toni