Filters








346,160 Hits in 14.0 sec

Investigating Data Work Across Domains

Kathleen Pine, Claus Bossen, Naja Holten Møller, Milagros Miceli, Alex Jiahong Lu, Yunan Chen, Leah Horgan, Zhaoyuan Su, Gina Neff, Melissa Mazmanian
2022 CHI Conference on Human Factors in Computing Systems Extended Abstracts  
Further, In some cases, increased demands for data work have led to the formation of new occupations, whereas at other times data work has been added to the task portfolios of existing occupations and  ...  Thus, the evolving forms of data work are requiring individual and organizational resources, new and re-tooled practices and tools, development of new competences and skills, and creation of new functions  ...  ACKNOWLEDGMENTS We wish to thank Tawanna Dillahunt for her very helpful comments and feedback on this proposal.  ... 
doi:10.1145/3491101.3503724 fatcat:bsfcq2bt2rhc3lll5fgouv3baa

Domain-Specific Event Abstraction

Finn Klessascheck, Tom Lichtenstein, Martin Meier, Simon Remy, Jan Philipp Sachs, Luise Pufahl, Riccardo Miotto, Erwin Boettinger, Mathias Weske
2021 Business Information Systems  
We show that the method introduced generates semantically meaningful high-level events, suitable for process mining; it is evaluated on real-world patient treatment data of a large U.S. health system.  ...  In complex domains like healthcare, data is available only at different levels of granularity.  ...  This work was supported in part through the computational and data resources and staff expertise provided by Scientific Computing at the Icahn School of Medicine at Mount Sinai.  ... 
doi:10.52825/bis.v1i.39 fatcat:b6lvas6qhvdyjih3sm5o3mgybi

DACS: Domain Adaptation via Cross-domain Mixed Sampling [article]

Wilhelm Tranheden, Viktor Olsson, Juliano Pinto, Lennart Svensson
2020 arXiv   pre-print
In this paper we address the problem of unsupervised domain adaptation (UDA), which attempts to train on labelled data from one domain (source domain), and simultaneously learn from unlabelled data in  ...  However, these models typically do not generalize well when applied on new domains, especially when going from synthetic to real data.  ...  Acknowledgements Part of this work was carried out during a master thesis at Volvo Cars, who also provided the necessary hardware to facilitate our experiments.  ... 
arXiv:2007.08702v2 fatcat:swsf5xeyjndilovbucs4tly27q

Domain *

John D. McGregor
2004 Journal of Object Technology  
This time in Strategic Software Engineering I want to explore some of the implications of the increased recognition of the role of domain in software engineering.  ...  Domain plays an increasingly important role in our business. In fact, it is our business. The wildcard in the title indicates that there are several domain-related issues in software engineering.  ...  They build one model on the abstract data types (ADT) that are used in the implementations of the applications.  ... 
doi:10.5381/jot.2004.3.7.c6 fatcat:t7nqbdrgbva3rbt6xrbgtw75le

Defining Domain-Independent Discovery Informatics [article]

William W. Agresti
2017 arXiv   pre-print
The state of DI is traced across various reference sources and the literature on the fourth paradigm of the scientific method.  ...  This paper presents a personal account of the early legacy of discovery informatics, especially surrounding the first published definition of domain-independent DI.  ...  Based on our experiences, we believed there was outstanding data analytics work going on within domains, but not a lot of sharing across domains.  ... 
arXiv:1703.01298v1 fatcat:iblrdlekingkfjtfrp5pukdq4y

Immanent Domain

Dana Cuff
2003 Journal of Architectural Education  
From cell phones to wireless local area networks, smart buildings to embedded vehicular computers, an invisible web of digital technology already lies across the visible world creating new space for work  ...  , data, advertisement, investigation, communication, intimacy, and danger.  ...  It also represents the possibility of new knowledge that will enhance safety, inform action, and provide perspective.  ... 
doi:10.1162/104648803322336575 fatcat:5vejqzfacrhmvouv2w4ck3fncq

Generalizing to Unseen Domains: A Survey on Domain Generalization [article]

Jindong Wang, Cuiling Lan, Chang Liu, Yidong Ouyang, Tao Qin, Wang Lu, Yiqiang Chen, Wenjun Zeng, Philip S. Yu
2022 arXiv   pre-print
Great progress has been made in the area of domain generalization for years. This paper presents the first review of recent advances in this area.  ...  Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain.  ...  Many works investigate DG on classification.  ... 
arXiv:2103.03097v7 fatcat:ry4ggjl63bhlzdhg3gojvyk2v4

Domain Transformer: Predicting Samples of Unseen, Future Domains [article]

Johannes Schneider
2022 arXiv   pre-print
Our evaluation of CNNs on image data confirms the usefulness of the approach.  ...  It also achieves very good results on the well-known problem of unsupervised domain adaption, where only labels but no samples have to be predicted.  ...  They have been shown to work well when domains are similar (from the perspective of the investigated network).  ... 
arXiv:2106.06057v2 fatcat:aot5xejtwbhpfdwtn24zim7uxe

Accounting for Unobserved Confounding in Domain Generalization [article]

Alexis Bellot, Mihaela van der Schaar
2022 arXiv   pre-print
We demonstrate the empirical performance of our approach on healthcare data from different modalities, including image, speech and tabular data.  ...  This paper investigates the problem of learning robust, generalizable prediction models from a combination of multiple datasets and qualitative assumptions about the underlying data-generating model.  ...  Acknowledgements This work was supported by the Alan Turing Institute under the EPSRC grant EP/N510129/1, the ONR and the NSF grants number 1462245 and number 1533983.  ... 
arXiv:2007.10653v6 fatcat:6n3p7vebpzeczfdxbtau336u2y

Improving Multi-Domain Generalization through Domain Re-labeling [article]

Kowshik Thopalli, Sameeksha Katoch, Andreas Spanias, Pavan Turaga, Jayaraman J. Thiagarajan
2021 arXiv   pre-print
In this paper, we focus on the challenging problem of multi-source zero-shot DG, where labeled training data from multiple source domains is available but with no access to data from the target domain.  ...  Though this problem has become an important topic of research, surprisingly, the simple solution of pooling all source data together and training a single classifier is highly competitive on standard benchmarks  ...  ACKNOWLEDGEMENTS This work was performed under the auspices of the U.S. Department of Energy by the Lawrence Livermore National Laboratory under Contract No.  ... 
arXiv:2112.09802v1 fatcat:nluhqosqo5dmtcom4wkzmr7wny

Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay [article]

Qicheng Lao, Xiang Jiang, Mohammad Havaei, Yoshua Bengio
2020 arXiv   pre-print
., the drift in the conditional distribution of labels given the input data, or the domain drift, i.e., the drift in the marginal distribution of the input data.  ...  This paper aims to tackle this challenge in the context of continuous domain adaptation, where the model is required to learn new tasks adapted to new domains in a non-stationary environment while maintaining  ...  Note that although derived from a new perspective, our objective function has a similar form as the upper bound of the target domain error 2 in domain adaptation theory (Ben-David et al., 2010) .  ... 
arXiv:2003.04382v1 fatcat:mlksrllqkjegtfwrhph4j3bxwi

Multi-task Domain Adaptation for Sequence Tagging [article]

Nanyun Peng, Mark Dredze
2017 arXiv   pre-print
Experiments show that multi-task domain adaptation works better than disjoint domain adaptation for each task, and achieves the state-of-the-art results for both tasks in the social media domain.  ...  Many domain adaptation approaches rely on learning cross domain shared representations to transfer the knowledge learned in one domain to other domains.  ...  Related Work The previous work on domain adaptation exclusively focused on building a unified model for a task across domain.  ... 
arXiv:1608.02689v2 fatcat:rhp3xb64irhv3ghzu3jwkwa5cq

Gradual Domain Adaptation without Indexed Intermediate Domains [article]

Hong-You Chen, Wei-Lun Chao
2022 arXiv   pre-print
In this paper, we investigate how to discover the sequence of intermediate domains when it is not already available.  ...  On benchmark data sets of GDA, we show that our approach, which we name Intermediate DOmain Labeler (IDOL), can lead to comparable or even better adaptation performance compared to the pre-defined domain  ...  We are thankful for the generous support of the computational resources by the Ohio Supercomputer Center.  ... 
arXiv:2207.04587v1 fatcat:ihzj3rqorrckxbovxpeif5343m

Modular Domain Adaptation [article]

Junshen K. Chen and Dallas Card and Dan Jurafsky
2022 arXiv   pre-print
We introduce two lightweight techniques for this scenario, and demonstrate that they reliably increase out-of-domain accuracy on four multi-domain text classification datasets when used with linear and  ...  Off-the-shelf models are widely used by computational social science researchers to measure properties of text, such as sentiment.  ...  Acknowledgements This research was supported in part by a seed grant from the Stanford Woods Institute for the Environment EVP and by Stanford Data Science.  ... 
arXiv:2204.14213v1 fatcat:cf7u2ucy4nesflgxjbb44ejc6y

The Biopolitical Public Domain [chapter]

Julie E. Cohen
2019 Between Truth and Power  
The idea of a public domain of personal data has two interrelated effects.  ...  on an industrial scale and to the outputs of such operations.  ...  to delay passage of copyrighted works into the public domain.  ... 
doi:10.1093/oso/9780190246693.003.0003 fatcat:36vgabrmeffwtmjdcjaeirye7m
« Previous Showing results 1 — 15 out of 346,160 results