Performance Analysis
RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting
The Rashomon effect is a mixed blessing in responsible machine learning.
ANT: Adaptive Noise Schedule for Time Series Diffusion Models
This highlights the importance of selecting an appropriate schedule for each dataset.
PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation Weiqin Y ang
Softmax Loss (SL) is widely applied in recommender systems (RS) and has demonstrated effectiveness.
NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
Machine learning craves high-quality data which is a major bottleneck during realistic deployment, as it takes abundant resources and massive human labor to collect and label data. Unfortunately, label noise where image data mismatches with incorrect label exists ubiquitously in all kinds of datasets, significantly degrading the learning performance of deep networks. Learning with Label Noise (LNL) has been a common strategy for mitigating the influence of noisy labels.
Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical Systems Kurt Butler
The TSCI approach is model-agnostic and can be used as a drop-in replacement for CCM and its generalizations.
Large Language Model Unlearning via Embedding-Corrupted Prompts
Instead of relying on the LLM itself to unlearn, we enforce an unlearned state during inference by employing a prompt classifier to identify and safeguard prompts to forget.
Learning Low-Rank Feature for Thorax Disease Classification
We study thorax disease classification in this paper.
Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network
Model Parsing defines the task of predicting hyperparameters of the generative model (GM), given a GM-generated image as the input.
Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering Dongxiao He
Graph Contrastive Learning (GCL) has emerged as a powerful approach for generating graph representations without the need for manual annotation. Most advanced GCL methods fall into three main frameworks: node discrimination, group discrimination, and bootstrapping schemes, all of which achieve comparable performance. However, the underlying mechanisms and factors that contribute to their effectiveness are not yet fully understood.