Titlebook: Machine Learning and Knowledge Discovery in Databases; European Conference, Massih-Reza Amini,Stéphane Canu,Grigorios Tsoumaka Conference p

FLAT

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

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

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

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

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

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

顯而易見

健忘癥

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

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