Deep Learning
Leveraging sparse and shared feature activations for disentangled representation learning
However, this is not always the case, as different tasks can compete with each other and lead to weaker models.
Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks
Yaqin Zhou, Shangqing Liu, Jingkai Siow, Xiaoning Du, Yang Liu
Neural Information Processing Systems http://nips.cc/
Training neural operators to preserve invariant measures of chaotic attractors
In this setting, neural operators trained to minimize squared error losses, while capable of accurate short-term forecasts, often fail to reproduce statistical or structural properties of the dynamics over longer time horizons and can yield degenerate results.
AGEM: Solving Linear Inverse Problems via Deep Priors and Sampling
Bichuan Guo, Yuxing Han, Jiangtao Wen
Neural Information Processing Systems http://nips.cc/
ScalableRule-Based RepresentationLearningfor InterpretableClassification
Ensemble methodsand fuzzy/soft rules are commonly used to improve performance, but they sacrifice the model interpretability.
Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
Pre-trained large language models (LLMs) based on Transformer have demonstrated striking in-context learning (ICL) abilities.
Appendix
We summarize our notations in the following table for easy reference.