Titlebook: Machine Learning and Knowledge Discovery in Databases. Research Track; European Conference, Albert Bifet,Jesse Davis,Indrė Žliobaitė Confer

遍及

Fair Densest Subgraph Across Multiple Graphs while inducing a total density of at least . across the graph snapshots. We prove the .-hardness of the problem and propose two algorithms: an exponential time algorithm based on integer programming and a greedy algorithm. We present an extensive experimental study that shows that our algorithms ca

掺假

A Human-Centric Assessment of the Usefulness of Attribution Methods in Computer Visioneturns a usefulness ranking of the XAI models and also compares them with a human baseline. In a large-scale subject study, our results show that the acceptance rate increases from 64.2% without explanations to 86% with XAI methods and 92.7% when given human explanations. One particular model obtain

熔岩

Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resiliencentroduce Fast-FedUL, a tailored unlearning method for FL, which eliminates the need for retraining entirely. Through meticulous analysis of the target client’s influence on the global model in each round, we develop an algorithm to systematically remove the impact of the target client from the train

Notify

Input Compression with Positional Consistency for Efficient Training and Inference of Transformer Neng of compressed inputs without any changes to the underlying Transformer architecture. We detail compression-based augmentation methods for four different modalities – insignificant word pruning for text, resolution modulation for images, spatio-temporal resolution modulation for videos, and spectr

FISC

并排上下

消灭

有节制

Forehead-Lift

labyrinth

: A Transfer and Interpretable LLM-Enhanced Framework for New Intent Discoveryon knowledge from known to novel intents, facilitating the transfer of clear-cut knowledge about predictive distributions. The reliable knowledge interpretation module focuses on selecting characteristic samples from clusters related to new categories. It then employs the in-context learning capabil