SaDe: Learning Models that Provably Satisfy Domain Constraints

Goyal, Kshitij; Dumančić, Sebastijan; Blockeel, Hendrik

doi:10.48550/arxiv.2112.00552

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper also relates to the field of constrained machine learning because the syntax of the final model to be used in the system is constrained in a logical form (the product concept is encoded using a logical query in the system). There are approaches that can learn machine learning models under similar syntactic constraints [11]. In our work, however, we use decision trees to implicitly enforce such constraints and extract the model in the constrained form (product concept query) to be encoded in Tunify's system.…”

Section: Related Workmentioning

confidence: 99%

Automatic Generation of Product Concepts from Positive Examples, with an Application to Music Streaming

Goyal

Meert

Blockeel

et al. 2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

Internet based businesses and products (e.g. e-commerce, music streaming) are becoming more and more sophisticated every day with a lot of focus on improving customer satisfaction. A core way they achieve this is by providing customers with an easy access to their products by structuring them in catalogues using navigation bars and providing recommendations. We refer to these catalogues as product concepts, e.g. product categories on e-commerce websites, public playlists on music streaming platforms. These product concepts typically contain products that are linked with each other through some common features (e.g. a playlist of songs by the same artist). How they are defined in the backend of the system can be different for different products. In this work, we represent product concepts using database queries and tackle two learning problems. First, given sets of products that all belong to the same unknown product concept, we learn a database query that is a representation of this product concept. Second, we learn product concepts and their corresponding queries when the given sets of products are associated with multiple product concepts. To achieve these goals, we propose two approaches that combine the concepts of PU learning with Decision Trees and Clustering. Our experiments demonstrate, via a simulated setup for a music streaming service, that our approach is effective in solving these problems.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic Generation of Product Concepts from Positive Examples, with an Application to Music Streaming

Goyal

Meert

Blockeel

et al. 2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

show abstract

“…Other work attempts to apply domain knowledge constraints on the learning process in attempt to control the model's learning process [3,12,14,23]. DL2 [12] models logical constraints into the model to capture background knowledge in the form of logical reasoning.…”

Section: Domain Knowledge Constraintsmentioning

confidence: 99%

“…DL2 [12] models logical constraints into the model to capture background knowledge in the form of logical reasoning. Other approaches also attempt to model constraints as domain losses model [23] or a satisfiability problem [14].…”

Section: Domain Knowledge Constraintsmentioning

confidence: 99%

Constraining the Attack Space of Machine Learning Models with Distribution Clamping Preprocessing

Feng¹,

Jha²,

Prakash³

2022

Preprint

View full text Add to dashboard Cite

Preprocessing and outlier detection techniques have both been applied to neural networks to increase robustness with varying degrees of success. In this paper, we formalize the ideal preprocessor function as one that would take any input and set it to the nearest in-distribution input. In other words, we detect any anomalous pixels and set them such that the new input is in-distribution. We then illustrate a relaxed solution to this problem in the context of patch attacks. Specifically, we demonstrate that we can model constraints on the patch attack that specify regions as out of distribution. With these constraints, we are able to preprocess inputs successfully, increasing robustness on CARLA object detection.

show abstract

SaDe: Learning Models that Provably Satisfy Domain Constraints

Cited by 2 publications

References 0 publications

Automatic Generation of Product Concepts from Positive Examples, with an Application to Music Streaming

Automatic Generation of Product Concepts from Positive Examples, with an Application to Music Streaming

Constraining the Attack Space of Machine Learning Models with Distribution Clamping Preprocessing

Contact Info

Product

Resources

About