KDD 2024

   page       attach   
30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Barcelona, Spain, 25/08/2024–29/08/2024

KDD is the premier Data Science conference, hosting both a Research and an Applied Data Science Track.  A paper should either be submitted to the Research Track or the Applied Data Science Track but not both. The conference will take place in Barcelona, from August 25 to 29, 2024.

topics of interest

For the research track, we invite submission of papers describing innovative research on all aspects of knowledge discovery and data science, ranging from theoretical foundations to novel models and algorithms for data science problems in science, business, medicine, and engineering. Visionary papers on new and emerging topics are also welcome, as are application-oriented papers that make innovative technical contributions to research.  Topics of interest include, but are not limited to:

  • Data Science: Methods for analyzing social networks, time series, sequences, streams, text, web, graphs, rules, patterns, logs, IoT data, spatio-temporal data, biological data, scientific and business data; recommender systems, computational advertising, multimedia, finance, bioinformatics.
  • Big Data: Large-scale systems for data analysis, machine learning, optimization, sampling, summarization; parallel and distributed data science (cloud, map-reduce, federated learning); novel algorithmic and statistical techniques for big data; algorithmically-efficient data transformation and integration.
  • Foundations: Models and algorithms, asymptotic analysis; model selection, dimensionality reduction, relational/structured learning, matrix and tensor methods, probabilistic and statistical methods; deep learning, transfer learning, representation learning, meta learning, reinforcement learning; classification, clustering, regression, semi-supervised learning, self-supervised learning, few shot learning and unsupervised learning; personalization, security and privacy, visualization; fairness, interpretability, ethics and robustness.
works as
origin event for publication
page_white_acrobatApproximating Memorization Using Loss Surface Geometry for Dataset Pruning and Summarization (paper in proceedings, 2024) — Andrea Agiollo, Young In Kim, Rajiv Khanna
hosting event for talk
page_white_powerpointApproximating Memorization Using Loss Surface Geometry for Dataset Pruning and Summarization (KDD 2024, 27/08/2024) — Andrea Agiollo (Andrea Agiollo, Kim Young In, Rajiv Khanna)