ODD Workshop

Interesting benchmark for Fraud created by @awscloud @groverpr4 arxiv.org/abs/2208.14417

Estimating out-of-distribution (OOD) performance is hard because labeled data is expensive. Can we predict OOD performance w/ only _unlabeled data_? In our work (arxiv.org/pdf/2206.13089…), we show this can be done using models’ agreement. w/ @yidingjiang, Aditi R., @zicokolter

#CFP Our #KDD2022 workshop on anomaly and novelty detection is seeking for paper submissions. We commit to a non-archival workshop. Dual submission is allowed! Submission deadline: May 26th, 2022(23:59 UTC-12) Website: sites.google.com/view/andea2022… In conjunction with @kdd_news

Seeing a lot of great OSS forecasting packages taking shape lately! Greykite (brand new from LinkedIn): github.com/linkedin/greyk… Orbit (released last year by Uber): github.com/uber/orbit engineering.linkedin.com/blog/2021/grey…

While we wait for NSDI's sessions, we had a cool presentation today form Davide Sanvito, about our early results in rethinking system monitoring: "Learning What to Monitor for Efficient Anomaly Detection" just happened at #EuroMLSys @EuroSys_conf @robegs @sharan_7f000001

Excited about our accepted paper at @TheWebConf "MemStream: Memory-Based Streaming Anomaly Detection" Preprint: arxiv.org/abs/2106.03837 Code: github.com/Stream-AD/MemS… #TheWebConf #WWW2022 #TheWebConf2022

Outlier Detection? Anomaly Detection? Novelty Detection? Open Set Recognition? OOD Detection? 🤨 What are they?🤔 Are they different?🧐 How to solve them?😕 Check out our latest survey "Generalized OOD Detection" to answer them all! arxiv.org/abs/2110.11334 github.com/Jingkang50/OOD…

Looking to hire a post doc researcher at CMU, for a project on graph anomaly detection with neural networks. Job posting and details at @Heinz.html" target="_blank" rel="nofollow noopener">andrew.cmu.edu/user/lakoglu/p… Contact me at lakoglu@andrew.cmu.edu Please feel free to forward to whom you think would be interested.

@AzriAbdelghani @kdd_news @leman_akoglu @souravc83 @ManishGuptaMG1 @CharuAg99748546 @danaikoutra @vagelispapalex @SergeyI49013776 @jure @mattmayo13 @WSDMSocial Slides to some of the talks are available on the workshop website.

@odd_workshop @kdd_news @leman_akoglu @souravc83 @ManishGuptaMG1 @CharuAg99748546 @danaikoutra @vagelispapalex @SergeyI49013776 @jure @mattmayo13 @WSDMSocial It's my first time to attend KDD. A lot of interesting talks but unfortunately we can't attend all sessions. So could you please share slides or recording if possible ? Thank you

ODD Workshop at #KDD2021 starts from 8am Pacific time. There are 6 exciting keynote talks and a panel discussion on fairness in outlier detection. oddworkshop.github.io

Glad to announce our #KDD2021 Workshop on Outlier Detection and Description @odd_workshop. Jointly organized with Bryan Hooi, @leman_akoglu, @souravc83, Xiaodong Jiang, @ManishGuptaMG1 Deadline: May 20, 2021 Details: oddworkshop.github.io @kdd_news #Anomaly #DataScience

8. Anomaly Detection and Automated Labeling for Voter Registration File Changes Sam F Royston, Courtenay Cotton

6. Anomaly Alignment Across Multiple Attributed Networks Jie Zhang, Nannan Wu, Wenjun Wang, ying sun, Siddharth Bhatia 7. CSCAD: Correlation Structure-based Collective Anomaly Detection in Complex System Huiling Qin, Xianyuan Zhan, Yu Zheng

Accepted Papers at ODD 2021: 1. Scalable Change Point Detection for Dynamic Graphs @shenyangHuang, @grwip, @ReiRabb 2. Out-of-Distribution Detection and Fairness Assessment in Dermatology Hannah H Kim, Girmaw Abebe Tadesse, @RTFMCelia, @PhonesDrones, @krvarshney

8. Time Series Anomaly Detection for Cyber-physical Systems via Neural System Identification and Bayesian Filtering arxiv.org/abs/2106.07992 Cheng Feng, Pengwei Tian

7. Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization Ahmed Abdulaal, Zhuanghua Liu, Tomer Lancewicki

If you are attending #KDD2021, check out the following interesting outlier/anomaly detection related papers: 1. Deep Clustering-based Fair Outlier Detection arxiv.org/abs/2106.05127 by Hanyu Song, Peizhao Li, Hongfu Liu @kdd_news