Search Results for author:
Found 17 papers, 11 papers with code
Simplex Decomposition for Portfolio Allocation Constraints in Reinforcement Learning
In this paper, we propose a novel approach to handle allocation constraints based on a decomposition of the constraint action space into a set of unconstrained allocation problems.
RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos
Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance.
How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learning
We conduct experiments with SSL and AL on simulated data challenges and find that random sampling does not mitigate confirmation bias and, in some cases, leads to worse performance than supervised learning.
DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification
Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data.
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation
Secondly, we propose a novel inter-instance interaction using gate activation as a mask for self-attention.
Ranked #4 on
Video Instance Segmentation
on YouTube-VIS 2021
(using extra training data)
InstanceFormer: An Online Video Instance Segmentation Framework
We propose three novel components to model short-term and long-term dependency and temporal coherence.
Ranked #5 on
Video Instance Segmentation
on Youtube-VIS 2022 Validation
(using extra training data)
Towards a Holistic View on Argument Quality Prediction
While there are works on the automated estimation of argument strength, their scope is narrow: they focus on isolated datasets and neglect the interactions with related argument mining tasks, such as argument identification, evidence detection, or emotional appeal.
Active Learning for Argument Strength Estimation
High-quality arguments are an essential part of decision-making.
Adaptive Multi-Resolution Attention with Linear Complexity
Transformers have improved the state-of-the-art across numerous tasks in sequence modeling.
NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification
Malicious software (malware) poses an increasing threat to the security of communication systems as the number of interconnected mobile devices increases exponentially.
Argument Mining Driven Analysis of Peer-Reviews
Peer reviewing is a central process in modern research and essential for ensuring high quality and reliability of published work.
Diversity Aware Relevance Learning for Argument Search
In this work, we focus on the problem of retrieving relevant arguments for a query claim covering diverse aspects.
Matching the Clinical Reality: Accurate OCT-Based Diagnosis From Few Labels
Furthermore, our experiments show that exponential moving average (EMA) of model parameters, which is a component of both algorithms, is not needed for our classification problem, as disabling it leaves the outcome unchanged.
Ranked #3 on
Retinal OCT Disease Classification
on OCT2017
Retinal OCT Disease Classification
Semi-Supervised Image Classification
+1
Learning Self-Expression Metrics for Scalable and Inductive Subspace Clustering
Consequently, our model benefits from a constant number of parameters and a constant-size memory footprint, allowing it to scale to considerably larger datasets.
PushNet: Efficient and Adaptive Neural Message Passing
We find that our models outperform competitors on all datasets in terms of accuracy with statistical significance.
Knowledge Graph Entity Alignment with Graph Convolutional Networks: Lessons Learned
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 for this task.
Ranked #33 on
Entity Alignment
on DBP15k zh-en
TACAM: Topic And Context Aware Argument Mining
In previous works, the usual approach is to use a standard search engine to extract text parts which are relevant to the given topic and subsequently use an argument recognition algorithm to select arguments from them.
