FLAT
发表于 2025-3-28 17:51:44
Class-Incremental Learning via Knowledge Amalgamations methods have been proposed to address the catastrophic forgetting problem where an agent loses its generalization power of old tasks while learning new tasks. We put forward an alternative strategy to handle the catastrophic forgetting with knowledge amalgamation (CFA), which learns a student netw
Agility
发表于 2025-3-28 22:46:20
Trigger Detection for the sPHENIX Experiment via Bipartite Graph Networks with Set Transformerlso plays a vital role in facilitating the downstream offline data analysis process. The sPHENIX detector, located at the Relativistic Heavy Ion Collider in Brookhaven National Laboratory, is one of the largest nuclear physics experiments on a world scale and is optimized to detect physics processes
Stable-Angina
发表于 2025-3-29 02:46:59
Understanding Difficulty-Based Sample Weighting with a Universal Difficulty Measureto calculate their weights. In this study, this scheme is called difficulty-based weighting. Two important issues arise when explaining this scheme. First, a unified difficulty measure that can be theoretically guaranteed for training samples does not exist. The learning difficulties of the samples
murmur
发表于 2025-3-29 03:37:54
Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networksmodels without access to past data. Current methods focus only on selecting a sub-network for a new task that reduces forgetting of past tasks. However, this selection could limit the forward transfer of . past knowledge that helps in future learning. Our study reveals that satisfying both objective
Medicare
发表于 2025-3-29 09:47:53
PrUE: Distilling Knowledge from Sparse Teacher Networkshead on deployment. To compress these models, knowledge distillation was proposed to transfer knowledge from a cumbersome (teacher) network into a lightweight (student) network. However, guidance from a teacher does not always improve the generalization of students, especially when the size gap betw
Interstellar
发表于 2025-3-29 12:05:38
Fooling Partial Dependence via Data Poisoningut that such explanations are not robust nor trustworthy, and they can be fooled. This paper presents techniques for attacking Partial Dependence (plots, profiles, PDP), which are among the most popular methods of explaining any predictive model trained on tabular data. We showcase that PD can be ma
ACME
发表于 2025-3-29 18:15:14
http://reply.papertrans.cn/63/6206/620516/620516_47.png
显而易见
发表于 2025-3-29 23:26:41
http://reply.papertrans.cn/63/6206/620516/620516_48.png
健忘症
发表于 2025-3-30 00:37:07
Hypothesis Testing for Class-Conditional Label Noiseactitioner already has preconceptions on possible distortions that may have affected the labels, which allow us to pose the task as the design of hypothesis tests. As a first approach, we focus on scenarios where a given dataset of instance-label pairs has been corrupted with ., as opposed to ., wit
Fortify
发表于 2025-3-30 06:59:23
On the Prediction Instability of Graph Neural Networksst in machine learning systems. In this paper, we systematically assess the prediction instability of node classification with state-of-the-art Graph Neural Networks (GNNs). With our experiments, we establish that multiple instantiations of popular GNN models trained on the same data with the same m