76 citations · 126 across the 14 of their papers we have counts for
16 papers
How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learning
Sandra Gilhuber, Rasmus Hvingelby, Mang Ling Ada Fok +1
Do we need active learning? The rise of strong deep semi-supervised methods raises doubt about the usability of active learning in limited labeled data settings. This is caused by…
DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification
Sandra Gilhuber, Julian Busch, Daniel Rotthues +2
Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data. To keep annotation costs low, active g…
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation
Tanveer Hannan, Rajat Koner, Maximilian Bernhard +5
Recent trends in Video Instance Segmentation (VIS) have seen a growing reliance on online methods to model complex and lengthy video sequences. However, the degradation of represen…
InstanceFormer: An Online Video Instance Segmentation Framework
Rajat Koner, Tanveer Hannan, Suprosanna Shit +4
Recent transformer-based offline video instance segmentation (VIS) approaches achieve encouraging results and significantly outperform online approaches. However, their reliance on…
Towards a Holistic View on Argument Quality Prediction
Michael Fromm, Max Berrendorf, Johanna Reiml +4
Argumentation is one of society's foundational pillars, and, sparked by advances in NLP and the vast availability of text data, automated mining of arguments receives increasing at…
Active Learning for Argument Strength Estimation
Nataliia Kees, Michael Fromm, Evgeniy Faerman +1
High-quality arguments are an essential part of decision-making. Automatically predicting the quality of an argument is a complex task that recently got much attention in argument…
Adaptive Multi-Resolution Attention with Linear Complexity
Yao Zhang, Yunpu Ma, Thomas Seidl +1
Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity w.r.t the sequence length, the…
NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification
Julian Busch, Anton Kocheturov, Volker Tresp +1
Malicious software (malware) poses an increasing threat to the security of communication systems as the number of interconnected mobile devices increases exponentially. While some…
Argument Mining Driven Analysis of Peer-Reviews
Michael Fromm, Evgeniy Faerman, Max Berrendorf +7
Peer reviewing is a central process in modern research and essential for ensuring high quality and reliability of published work. At the same time, it is a time-consuming process a…
Diversity Aware Relevance Learning for Argument Search
Michael Fromm, Max Berrendorf, Sandra Obermeier +2
In this work, we focus on the problem of retrieving relevant arguments for a query claim covering diverse aspects. State-of-the-art methods rely on explicit mappings between claims…
Matching the Clinical Reality: Accurate OCT-Based Diagnosis From Few Labels
Valentyn Melnychuk, Evgeniy Faerman, Ilja Manakov +1
Unlabeled data is often abundant in the clinic, making machine learning methods based on semi-supervised learning a good match for this setting. Despite this, they are currently re…
Learning Self-Expression Metrics for Scalable and Inductive Subspace Clustering
Julian Busch, Evgeniy Faerman, Matthias Schubert +1
Subspace clustering has established itself as a state-of-the-art approach to clustering high-dimensional data. In particular, methods relying on the self-expressiveness property ha…
PushNet: Efficient and Adaptive Neural Message Passing
Julian Busch, Jiaxing Pi, Thomas Seidl
Message passing neural networks have recently evolved into a state-of-the-art approach to representation learning on graphs. Existing methods perform synchronous message passing al…
Knowledge Graph Entity Alignment with Graph Convolutional Networks: Lessons Learned
Max Berrendorf, Evgeniy Faerman, Valentyn Melnychuk +2
In this work, we focus on the problem of entity alignment in Knowledge Graphs (KG) and we report on our experiences when applying a Graph Convolutional Network (GCN) based model fo…
TACAM: Topic And Context Aware Argument Mining
Michael Fromm, Evgeniy Faerman, Thomas Seidl
In this work we address the problem of argument search. The purpose of argument search is the distillation of pro and contra arguments for requested topics from large text corpora.…
KDD-SC: Subspace Clustering Extensions for Knowledge Discovery Frameworks
Stephan Günnemann, Hardy Kremer, Matthias Hannen +1
Analyzing high dimensional data is a challenging task. For these data it is known that traditional clustering algorithms fail to detect meaningful patterns. As a solution, subspace…