skip to main content

This content will become publicly available on May 21, 2023

Title: Fairkit-learn: A Fairness Evaluation and Comparison Toolkit
Advances in how we build and use software, specifically the integration of machine learning for decision making, have led to widespread concern around model and software fairness. We present fairkit-learn, an interactive Python toolkit designed to support data scientists' ability to reason about and understand model fairness. We outline how fairkit-learn can support model training, evaluation, and comparison and describe the potential benefit that comes with using fairkit-learn in comparison to the state-of-the-art. Fairkit-learn is open source at https://go.gmu.edu/fairkit-learn/.
Authors:
;
Award ID(s):
1763423
Publication Date:
NSF-PAR ID:
10334566
Journal Name:
Proceedings of the Demonstrations Track at the 44th International Conference on Software Engineering (ICSE)
Page Range or eLocation-ID:
70-74
Sponsoring Org:
National Science Foundation
More Like this
  1. A goal of software engineering research is advancing software quality and the success of the software engineering process. However, while recent studies have demonstrated a new kind of defect in software related to its ability to operate in fair and unbiased manner, software engineering has not yet wholeheartedly tackled these new kinds of defects, thus leaving software vulnerable. This paper outlines a vision for how software engineering research can help reduce fairness defects and represents a call to action by the software engineering research community to reify that vision. Modern software is riddled with examples of biased behavior, from automatedmore »translation injecting gender stereotypes, to vision systems failing to see faces of certain races, to the US criminal justice system relying on biased computational assessments of crime recidivism. While systems may learn bias from biased data, bias can also emerge from ambiguous or incomplete requirement specification, poor design, implementation bugs, and unintended component interactions. We argue that software fairness is analogous to software quality, and that numerous software engineering challenges in the areas of requirements, specification, design, testing, and verification need to be tackled to solve this problem.« less
  2. Graph mining is an essential component of recommender systems and search engines. Outputs of graph mining models typically provide a ranked list sorted by each item's relevance or utility. However, recent research has identified issues of algorithmic bias in such models, and new graph mining algorithms have been proposed to correct for bias. As such, algorithm developers need tools that can help them uncover potential biases in their models while also exploring the impacts of correcting for biases when employing fairness-aware algorithms. In this paper, we present FairRankVis, a visual analytics framework designed to enable the exploration of multi-class biasmore »in graph mining algorithms. We support both group and individual fairness levels of comparison. Our framework is designed to enable model developers to compare multi-class fairness between algorithms (for example, comparing PageRank with a debiased PageRank algorithm) to assess the impacts of algorithmic debiasing with respect to group and individual fairness. We demonstrate our framework through two usage scenarios inspecting algorithmic fairness.« less
  3. Abstract Engineering students need to spend time engaging in mathematical modeling tasks to reinforce their learning of mathematics through its application to authentic problems and real world design situations. Technological tools and resources can support this kind of learning engagement. We produced an online module that develops students’ mathematical modeling skills while developing knowledge of the fundamentals of rainfall-runoff processes and engineering design. This study examined how 251 students at two United States universities perceived mathematical modeling as implemented through the online module over a 5-year period. We found, subject to the limitation that these are perceptions from not allmore »students, that: (a) the module allowed students to be a part of the modeling process; (b) using technology, such as modeling software and online databases, in the module helped students to understand what they were doing in mathematical modeling; (c) using the technology in the module helped students to develop their skill set; and (d) difficulties with the technology and/or the modeling decisions they had to make in the module activities were in some cases barriers that interfered with students’ ability to learn. We advocate for instructors to create modules that: (a) are situated within a real-world context, requiring students to model mathematically to solve an authentic problem; (b) take advantage of digital tools used by engineers to support students’ development of the mathematical and engineering skills needed in the workforce; and (c) use student feedback to guide module revisions.« less
  4. There has been dramatic growth in the number of makerspaces at educational institutions. More research is needed to understand student interactions in these spaces and how these spaces should be designed to support student learning. This project uses network analysis techniques to study the network of activities in a makerspace that lead to successful student experiences. The proposed analyses will model a makerspace as a network of interactions between equipment, staff, and students. Results from this study will help educators to 1) identify and remove previously unknown hurdles for students who rarely use the space, 2) design an effective spacemore »using limited resources, 3) understand the impact of new equipment or staff, and 4) create learning opportunities such as workshops and curriculum integration that increase student learning. The new knowledge produced by this project may be useful for maximizing equipment and support infrastructure, and for guiding new equipment purchases. Thus, the results will support further development of effective makerspaces. This project hypothesizes that network-level analyses and metrics can provide valuable insights into student learning in makerspaces and will support what-if scenarios for proposed changes in spaces. Systems modeling and analysis have been used successfully to understand complex human and biological networks. In the context of makerspaces, this technique will provide measures of interaction between system components such as students, staff, and equipment. The analyses will identify the system components that are frequently used when students work in the makerspace over multiple visits. The project will allow for the comparison of makerspaces that have different levels of integration with the curriculum and methods of student introduction (pop-up classes, tours, extra-curricular competitions, advertising, and bring a friend). Demonstration of the effectiveness of the analyses in characterizing makerspaces and the ease of data collection will help support the use of this approach in future work that compares makerspaces nationwide. Current results explore the order in which students choose to learn and use the tools in the space, which tools/features are used most frequently and how the data from the daily entry/exit surveys compares to the end-of-semester self-reports. A key question in this research, especially for making it adoptable by other universities, is if end-of-semester, self-reported data is accurate enough to create informative, actionable guidance from the network models without requiring the daily tool usage data.« less
  5. Obeid, Iyad ; Picone, Joseph ; Selesnick, Ivan (Ed.)
    The Neural Engineering Data Consortium (NEDC) is developing a large open source database of high-resolution digital pathology images known as the Temple University Digital Pathology Corpus (TUDP) [1]. Our long-term goal is to release one million images. We expect to release the first 100,000 image corpus by December 2020. The data is being acquired at the Department of Pathology at Temple University Hospital (TUH) using a Leica Biosystems Aperio AT2 scanner [2] and consists entirely of clinical pathology images. More information about the data and the project can be found in Shawki et al. [3]. We currently have a Nationalmore »Science Foundation (NSF) planning grant [4] to explore how best the community can leverage this resource. One goal of this poster presentation is to stimulate community-wide discussions about this project and determine how this valuable resource can best meet the needs of the public. The computing infrastructure required to support this database is extensive [5] and includes two HIPAA-secure computer networks, dual petabyte file servers, and Aperio’s eSlide Manager (eSM) software [6]. We currently have digitized over 50,000 slides from 2,846 patients and 2,942 clinical cases. There is an average of 12.4 slides per patient and 10.5 slides per case with one report per case. The data is organized by tissue type as shown below: Filenames: tudp/v1.0.0/svs/gastro/000001/00123456/2015_03_05/0s15_12345/0s15_12345_0a001_00123456_lvl0001_s000.svs tudp/v1.0.0/svs/gastro/000001/00123456/2015_03_05/0s15_12345/0s15_12345_00123456.docx Explanation: tudp: root directory of the corpus v1.0.0: version number of the release svs: the image data type gastro: the type of tissue 000001: six-digit sequence number used to control directory complexity 00123456: 8-digit patient MRN 2015_03_05: the date the specimen was captured 0s15_12345: the clinical case name 0s15_12345_0a001_00123456_lvl0001_s000.svs: the actual image filename consisting of a repeat of the case name, a site code (e.g., 0a001), the type and depth of the cut (e.g., lvl0001) and a token number (e.g., s000) 0s15_12345_00123456.docx: the filename for the corresponding case report We currently recognize fifteen tissue types in the first installment of the corpus. The raw image data is stored in Aperio’s “.svs” format, which is a multi-layered compressed JPEG format [3,7]. Pathology reports containing a summary of how a pathologist interpreted the slide are also provided in a flat text file format. A more complete summary of the demographics of this pilot corpus will be presented at the conference. Another goal of this poster presentation is to share our experiences with the larger community since many of these details have not been adequately documented in scientific publications. There are quite a few obstacles in collecting this data that have slowed down the process and need to be discussed publicly. Our backlog of slides dates back to 1997, meaning there are a lot that need to be sifted through and discarded for peeling or cracking. Additionally, during scanning a slide can get stuck, stalling a scan session for hours, resulting in a significant loss of productivity. Over the past two years, we have accumulated significant experience with how to scan a diverse inventory of slides using the Aperio AT2 high-volume scanner. We have been working closely with the vendor to resolve many problems associated with the use of this scanner for research purposes. This scanning project began in January of 2018 when the scanner was first installed. The scanning process was slow at first since there was a learning curve with how the scanner worked and how to obtain samples from the hospital. From its start date until May of 2019 ~20,000 slides we scanned. In the past 6 months from May to November we have tripled that number and how hold ~60,000 slides in our database. This dramatic increase in productivity was due to additional undergraduate staff members and an emphasis on efficient workflow. The Aperio AT2 scans 400 slides a day, requiring at least eight hours of scan time. The efficiency of these scans can vary greatly. When our team first started, approximately 5% of slides failed the scanning process due to focal point errors. We have been able to reduce that to 1% through a variety of means: (1) best practices regarding daily and monthly recalibrations, (2) tweaking the software such as the tissue finder parameter settings, and (3) experience with how to clean and prep slides so they scan properly. Nevertheless, this is not a completely automated process, making it very difficult to reach our production targets. With a staff of three undergraduate workers spending a total of 30 hours per week, we find it difficult to scan more than 2,000 slides per week using a single scanner (400 slides per night x 5 nights per week). The main limitation in achieving this level of production is the lack of a completely automated scanning process, it takes a couple of hours to sort, clean and load slides. We have streamlined all other aspects of the workflow required to database the scanned slides so that there are no additional bottlenecks. To bridge the gap between hospital operations and research, we are using Aperio’s eSM software. Our goal is to provide pathologists access to high quality digital images of their patients’ slides. eSM is a secure website that holds the images with their metadata labels, patient report, and path to where the image is located on our file server. Although eSM includes significant infrastructure to import slides into the database using barcodes, TUH does not currently support barcode use. Therefore, we manage the data using a mixture of Python scripts and manual import functions available in eSM. The database and associated tools are based on proprietary formats developed by Aperio, making this another important point of community-wide discussion on how best to disseminate such information. Our near-term goal for the TUDP Corpus is to release 100,000 slides by December 2020. We hope to continue data collection over the next decade until we reach one million slides. We are creating two pilot corpora using the first 50,000 slides we have collected. The first corpus consists of 500 slides with a marker stain and another 500 without it. This set was designed to let people debug their basic deep learning processing flow on these high-resolution images. We discuss our preliminary experiments on this corpus and the challenges in processing these high-resolution images using deep learning in [3]. We are able to achieve a mean sensitivity of 99.0% for slides with pen marks, and 98.9% for slides without marks, using a multistage deep learning algorithm. While this dataset was very useful in initial debugging, we are in the midst of creating a new, more challenging pilot corpus using actual tissue samples annotated by experts. The task will be to detect ductal carcinoma (DCIS) or invasive breast cancer tissue. There will be approximately 1,000 images per class in this corpus. Based on the number of features annotated, we can train on a two class problem of DCIS or benign, or increase the difficulty by increasing the classes to include DCIS, benign, stroma, pink tissue, non-neoplastic etc. Those interested in the corpus or in participating in community-wide discussions should join our listserv, nedc_tuh_dpath@googlegroups.com, to be kept informed of the latest developments in this project. You can learn more from our project website: https://www.isip.piconepress.com/projects/nsf_dpath.« less