Statistical Learning
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.
An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling Shenbao Y u
By exploiting students' response logs, SCM aims to predict their exercise
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.
Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning Wenke Huang 1, Mang Y e
Existing backdoor defense methods typically require either homogeneous assumption, validation datasets, or client optimization conflicts.
EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free Probing
Specifically, it achieves 93.9%, 96.5%, and 94.6% Recall@1 on the MSLS V alidation, Pitts250k-test, and SPED datasets, respectively, while saving 64.3% of trainable parameters compared with the existing SOT A PEFT method.
Unleashing Region Understanding in Intermediate Layers for MLLM-based Referring Expression Generation
On the other hand, complicated sentences could easily increase the probability of hallucinations.
EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection
This study proposes a novel framework, Event-based Graph Spatiotemporal Sensitive Transformer (EGSST), for the exploitation of spatial and temporal properties of event data.