CISPA @ NeurIPS 2024 in Vancouver

The NeurIPS Conference (Conference on Neural Information Processing Systems) is a leading annual event in the fields of machine learning, artificial intelligence, and computational neuroscience. At last week's 2024 edition, the research community came together to discuss emerging trends in the field and share their latest findings. Among them were numerous CISPA researchers showcasing their groundbreaking research.

The following papers by CISPA authors were presented at NeurIPS 2024 in Vancouver:

• Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models

Hui-Po Wang, Mario Fritz

• Spectral Graph Pruning Against Over-Squashing and Over-Smoothing

Adarsh Jamadandi, Celia Rubio-Madrigal, Rebekka Burkholz

• Causal Discovery from Event Sequences by Local Cause-Effect Attribution

Joscha Cüppers, Sascha Xu, Ahmed Musa, Jilles Vreeken

• Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models

Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch

• LLM Dataset Inference: Did you train on my dataset?

Pratyush Maini, Hengrui Jia, Nicolas Papernot, Adam Dziedzic

• Localizing Memorization in SSL Vision Encoders

Wenhao Wang, Adam Dziedzic, Michael Backes, Franziska Boenisch

• Open LLMs are Necessary for Private Adaptations and Outperform their Closed Alternatives

Vincent Hanke, Tom Blanchard, Franziska Boenisch, Iyiola Emmanuel Olatunji, Michael Backes, Adam Dziedzic

• ​​​​​​​​​​​​​​Representation noising effectively prevents harmful fine-tuning on LLMs

​​​​​​​Domenic Rosati, Jan Wehner, Kai Williams, Łukasz Bartoszcze, David Atanasov, Robie Gonzales, Subhabrata Majumdar, Carsten Maple, Hassan Sajjad, Frank Rudzicz

• ​​​​​​​​​​​​​​Stabilized Proximal-Point Methods for Federated Optimization

​​​​​​​​​​​​​​Xiaowen Jiang, Anton Rodomanov, Sebastian U Stich

• ​​​​​​​Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction

​​​​​​​Anton Rodomanov, Xiaowen Jiang, Sebastian U Stich

• ​​​​​​​Training GNNs in Balance by Dynamic Rescaling

Nimrah Mustafa, Rebekka Burkholz

• Pruning neural network models for gene regulatory dynamics using data and domain knowledge​​​​​​​​​​​​​​​​​​​​

​​​​​​​Intekhab Hossain, Jonas Fischer, Rebekka Burkholz, John Quackenbush

• Learning Better Representations From Less Data For Propositional Satisfiability

​​​​​​​Mohamed Ghanem, Frederik Schmitt, Julian Siber, Bernd Finkbeiner

• Hierarchical Uncertainty Exploration via Feedforward Posterior Trees

​​​​​​​Elias Nehme, Rotem Mulayoff, Tomer Michaeli​​​​​​​​​​​​​​​​​​​​​