Skip to content

Commit

Permalink
add seminar:5
Browse files Browse the repository at this point in the history
  • Loading branch information
Nadia DAOUDI committed Nov 16, 2023
1 parent 1b6d9d3 commit f9f1c51
Show file tree
Hide file tree
Showing 2 changed files with 52 additions and 29 deletions.
Binary file added img/benjamin.jpg
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
81 changes: 52 additions & 29 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -168,41 +168,64 @@ <h2>Prof. Dr. Jacques Klein</h2>
<div class="col-lg-12 col-md-10 col-sm-10 col-xs-10 upcomingevent wow zoomIn" data-wow-delay="0.1s">
<div class="container">

<div class="frame-title">
<h2>Upcoming Seminars<h2>
</div>
<div class="frame-title">
<h2>Upcoming Seminars<h2>
</div>

<div class="event-frame">
<div class="event">
<div class="presenter-details">
<img src="img/gohar.jpg">
<h5> Usman Gohar </h5>
<p> Iowa State University </p>
</div>
<div class="event-info">
<h3>Towards Understanding Fairness and its Composition in Ensemble Machine Learning</h3>
<p> Machine Learning (ML) software has been widely adopted in modern society, with reported fairness implications for minority groups based on race, sex, age, etc.
Many recent works have proposed methods to measure and mitigate algorithmic bias in ML models. The existing approaches focus on single classifier-based ML models.
However, real-world ML models are often composed of multiple independent or dependent learners in an ensemble (e.g., Random Forest), where the fairness composes in a non-trivial way.
How does fairness compose in ensembles? What are the fairness impacts of the learners on the ultimate fairness of the ensemble? Can fair learners result in an unfair ensemble?
Furthermore, studies have shown that hyperparameters influence the fairness of ML models. Ensemble hyperparameters are more complex since they affect how learners are combined in
different categories of ensembles. In this paper, we comprehensively study popular real-world ensembles: Bagging, Boosting, Stacking, and Voting. We have developed a benchmark
of 168 ensemble models collected from Kaggle on four popular fairness datasets. We use existing fairness metrics to understand the composition of fairness. Our results show that
ensembles can be designed to be fairer without using mitigation techniques. We also identify the interplay between fairness composition and data characteristics to guide fair
ensemble design.</p>
<p><b><span class="black-underligned">Presentation Date:</span></b> <span class="black"><strong>Monday, November 20, 2023 at 4:00 PM CET</strong></span></p>
<div class="event-frame">

<div class="event">
<div class="presenter-details">
<img src="img/gohar.jpg">
<h5> Usman Gohar </h5>
<p> Iowa State University </p>
</div>
<div class="event-info">
<h3>Towards Understanding Fairness and its Composition in Ensemble Machine Learning</h3>
<p> Machine Learning (ML) software has been widely adopted in modern society, with reported fairness implications for minority groups based on race, sex, age, etc.
Many recent works have proposed methods to measure and mitigate algorithmic bias in ML models. The existing approaches focus on single classifier-based ML models.
However, real-world ML models are often composed of multiple independent or dependent learners in an ensemble (e.g., Random Forest), where the fairness composes in a non-trivial way.
How does fairness compose in ensembles? What are the fairness impacts of the learners on the ultimate fairness of the ensemble? Can fair learners result in an unfair ensemble?
Furthermore, studies have shown that hyperparameters influence the fairness of ML models. Ensemble hyperparameters are more complex since they affect how learners are combined in
different categories of ensembles. In this paper, we comprehensively study popular real-world ensembles: Bagging, Boosting, Stacking, and Voting. We have developed a benchmark
of 168 ensemble models collected from Kaggle on four popular fairness datasets. We use existing fairness metrics to understand the composition of fairness. Our results show that
ensembles can be designed to be fairer without using mitigation techniques. We also identify the interplay between fairness composition and data characteristics to guide fair
ensemble design.</p>

<p><b><span class="black-underligned">Presentation Date:</span></b> <span class="black"><strong>Monday, November 20, 2023 at 4:00 PM CET</strong></span></p>

</div>
</div>
</div>
</div>



<div class="event">
<div class="presenter-details">
<img src="img/benjamin.jpg">
<h5> Benjamin Steenhoek </h5>
<p> Iowa State University </p>
</div>
<div class="event-info">
<h3>Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection</h3>
<p> Deep learning-based vulnerability detection has shown great performance and, in some studies, outperformed static analysis tools. However, the highest-performing
approaches use token-based transformer models, which are not the most efficient to capture code semantics required for vulnerability detection. In this paper, we propose
to combine such causal-based vulnerability detection algorithms with deep learning, aiming to achieve more efficient and effective vulnerability detection. Specifically,
we designed DeepDFA, a dataflow analysis-inspired graph learning framework and an embedding technique that enables graph learning to simulate dataflow computation. We show
that DeepDFA is both performant and efficient. DeepDFA outperformed all non-transformer baselines. It was trained in 9 minutes, 75x faster than the highest-performing baseline
model. When using only 50+ vulnerable and several hundreds of total examples as training data, the model retained the same performance as 100% of the dataset. DeepDFA also
generalized to real-world vulnerabilities in DbgBench; it detected 8.7 out of 17 vulnerabilities on average across folds and was able to distinguish between patched and buggy versions.
By combining DeepDFA with a large language model, we surpassed the state-of-the-art vulnerability detection performance on the Big-Vul dataset
with 96.46 F1 score, 97.82 precision, and 95.14 recall. </p>

<p><b><span class="black-underligned">Presentation Date:</span></b> <span class="black"><strong>Monday, December 4, 2023 at 3:00 PM CET</strong></span></p>

</div>
</div>



</div>
</div>
</div>

Expand Down

0 comments on commit f9f1c51

Please sign in to comment.