Search Results for author:
Found 15 papers, 11 papers with code
Towards Measuring Representational Similarity of Large Language Models
Understanding the similarity of the numerous released large language models (LLMs) has many uses, e. g., simplifying model selection, detecting illegal model reuse, and advancing our understanding of what makes LLMs perform well.
Similarity of Neural Network Models: A Survey of Functional and Representational Measures
Measuring similarity of neural networks to understand and improve their behavior has become an issue of great importance and research interest.
On the Prediction Instability of Graph Neural Networks
Instability of trained models, i. e., the dependence of individual node predictions on random factors, can affect reproducibility, reliability, and trust in machine learning systems.
Updating Embeddings for Dynamic Knowledge Graphs
To utilize information from Knowledge Graphs, many state-of-the-art machine learning approaches use embedding techniques.
Redescription Model Mining
This paper introduces Redescription Model Mining, a novel approach to identify interpretable patterns across two datasets that share only a subset of attributes and have no common instances.
Surfacing Estimation Uncertainty in the Decay Parameters of Hawkes Processes with Exponential Kernels
With a series of experiments with synthetic and real-world data from domains such as "classical" earthquake modeling or the manifestation of collective emotions on Twitter, we demonstrate that our proposed approach helps to quantify uncertainty and thereby to understand and fit Hawkes processes in practice.
A Comparative Evaluation of Quantification Methods
More generally, we find that the performance on multiclass quantification is inferior to the results obtained in the binary setting.
Volunteer contributions to Wikipedia increased during COVID-19 mobility restrictions
Wikipedia, the largest encyclopedia ever created, is a global initiative driven by volunteer contributions.
Computers and Society
The FairCeptron: A Framework for Measuring Human Perceptions of Algorithmic Fairness
The FairCeptron framework is an approach for studying perceptions of fairness in algorithmic decision making such as in ranking or classification.
Quota-based debiasing can decrease representation of already underrepresented groups
The most common approach to this issue is debiasing, for example via the introduction of quotas that ensure proportional representation of groups with respect to a certain, often binary attribute.
The Effects of Randomness on the Stability of Node Embeddings
We systematically evaluate the (in-)stability of state-of-the-art node embedding algorithms due to randomness, i. e., the random variation of their outcomes given identical algorithms and graphs.
Joint Multiclass Debiasing of Word Embeddings
Bias in Word Embeddings has been a subject of recent interest, along with efforts for its reduction.
The POLAR Framework: Polar Opposites Enable Interpretability of Pre-Trained Word Embeddings
We introduce POLAR - a framework that adds interpretability to pre-trained word embeddings via the adoption of semantic differentials.
Privacy Attacks on Network Embeddings
In that setting, we analyze whether after the removal of the node from the network and the deletion of the vector representation of the respective node in the embedding significant information about the link structure of the removed node is still encoded in the embedding vectors of the remaining nodes.
Discovering and Characterizing Mobility Patterns in Urban Spaces: A Study of Manhattan Taxi Data
By applying this combination of approaches to taxi data in Manhattan, we can discover and explain different patterns in human mobility that cannot be identified in a collective analysis.
