arXiv subjects

Ansgar Scherp

Publications and source records attributed to Ansgar Scherp.

At least 37 records · Page 2Linked to original sources

arXiv2024

Memorization of Named Entities in Fine-tuned BERT Models

Privacy preserving deep learning is an emerging field in machine learning that aims to mitigate the privacy risks in the use of deep neural networks. One such risk is training data extraction from language models that have been trained on datasets, which contain personal and privacy sensitive information. In our study, we investigate the extent of named entity memorization in fine-tuned BERT models. We use single-label text classification as representative downstream task and employ three different fine-tuning setups in our experiments, including one with Differential Privacy (DP). We create a large number of text samples from the fine-tuned BERT models utilizing a custom sequential sampling strategy with two prompting strategies. We search in these samples for named entities and check if they are also present in the fine-tuning datasets. We experiment with two benchmark datasets in the domains of emails and blogs. We show that the application of DP has a detrimental effect on the text generation capabilities of BERT. Furthermore, we show that a fine-tuned BERT does not generate more named entities specific to the fine-tuning dataset than a BERT model that is pre-trained only. This suggests that BERT is unlikely to emit personal or privacy sensitive named entities. Overall, our results are important to understand to what extent BERT-based services are prone to training data extraction attacks.

cs.CL↗

arXiv2024

Isotropy Matters: Soft-ZCA Whitening of Embeddings for Semantic Code Search

Low isotropy in an embedding space impairs performance on tasks involving semantic inference. Our study investigates the impact of isotropy on semantic code search performance and explores post-processing techniques to mitigate this issue. We analyze various code language models, examine isotropy in their embedding spaces, and its influence on search effectiveness. We propose a modified ZCA whitening technique to control isotropy levels in embeddings. Our results demonstrate that Soft-ZCA whitening improves the performance of pre-trained code language models and can complement contrastive fine-tuning.

cs.CL↗

arXiv2024

F -- A Model of Events based on the Foundational Ontology DOLCE+DnS Ultralite

The lack of a formal model of events hinders interoperability in distributed event-based systems. In this paper, we present a formal model of events, called Event-Model-F. The model is based on the foundational ontology DOLCE+DnS Ultralite (DUL) and provides comprehensive support to represent time and space, objects and persons, as well as mereological, causal, and correlative relationships between events. In addition, the Event-Model-F provides a flexible means for event composition, modeling event causality and event correlation, and representing different interpretations of the same event. The Event-Model-F is developed following the pattern-oriented approach of DUL, is modularized in different ontologies, and can be easily extended by domain specific ontologies.

cs.AI↗

arXiv2024

HyperAggregation: Aggregating over Graph Edges with Hypernetworks

HyperAggregation is a hypernetwork-based aggregation function for Graph Neural Networks. It uses a hypernetwork to dynamically generate weights in the size of the current neighborhood, which are then used to aggregate this neighborhood. This aggregation with the generated weights is done like an MLP-Mixer channel mixing over variable-sized vertex neighborhoods. We demonstrate HyperAggregation in two models, GraphHyperMixer is a model based on MLP-Mixer while GraphHyperConv is derived from a GCN but with a hypernetwork-based aggregation function. We perform experiments on diverse benchmark datasets for the vertex classification, graph classification, and graph regression tasks. The results show that HyperAggregation can be effectively used for homophilic and heterophilic datasets in both inductive and transductive settings. GraphHyperConv performs better than GraphHyperMixer and is especially strong in the transductive setting. On the heterophilic dataset Roman-Empire it reaches a new state of the art. On the graph-level tasks our models perform in line with similarly sized models. Ablation studies investigate the robustness against various hyperparameter choices. The implementation of HyperAggregation as well code to reproduce all experiments is available under https://github.com/Foisunt/HyperAggregation .

cs.LG↗

arXiv2024

POWN: Prototypical Open-World Node Classification

We consider the problem of \textit{true} open-world semi-supervised node classification, in which nodes in a graph either belong to known or new classes, with the latter not present during training. Existing methods detect and reject new classes but fail to distinguish between different new classes. We adapt existing methods and show they do not solve the problem sufficiently. We introduce a novel end-to-end approach for classification into known classes and new classes based on class prototypes, which we call Prototypical Open-World Learning for Node Classification (POWN). Our method combines graph semi-supervised learning, self-supervised learning, and pseudo-labeling to learn prototype representations of new classes in a zero-shot way. In contrast to existing solutions from the vision domain, POWN does not require data augmentation techniques for node classification. Experiments on benchmark datasets demonstrate the effectiveness of POWN, where it outperforms baselines by up to $20\%$ accuracy on the small and up to $30\%$ on the large datasets. Source code is available at https://github.com/Bobowner/POWN.

cs.LG↗

arXiv2024

Text Role Classification in Scientific Charts Using Multimodal Transformers

Text role classification involves classifying the semantic role of textual elements within scientific charts. For this task, we propose to finetune two pretrained multimodal document layout analysis models, LayoutLMv3 and UDOP, on chart datasets. The transformers utilize the three modalities of text, image, and layout as input. We further investigate whether data augmentation and balancing methods help the performance of the models. The models are evaluated on various chart datasets, and results show that LayoutLMv3 outperforms UDOP in all experiments. LayoutLMv3 achieves the highest F1-macro score of 82.87 on the ICPR22 test dataset, beating the best-performing model from the ICPR22 CHART-Infographics challenge. Moreover, the robustness of the models is tested on a synthetic noisy dataset ICPR22-N. Finally, the generalizability of the models is evaluated on three chart datasets, CHIME-R, DeGruyter, and EconBiz, for which we added labels for the text roles. Findings indicate that even in cases where there is limited training data, transformers can be used with the help of data augmentation and balancing methods. The source code and datasets are available on GitHub under https://github.com/hjkimk/text-role-classification

cs.CV↗

arXiv2023

GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding

Language models can serve as a valuable tool for software developers to increase productivity. Large generative models can be used for code generation and code completion, while smaller encoder-only models are capable of performing code search tasks using natural language queries.These capabilities are heavily influenced by the quality and diversity of the available training data. Source code datasets used for training usually focus on the most popular languages and testing is mostly conducted on the same distributions, often overlooking low-resource programming languages. Motivated by the NLP generalization taxonomy proposed by Hupkes et.\,al., we propose a new benchmark dataset called GenCodeSearchNet (GeCS) which builds upon existing natural language code search datasets to systemically evaluate the programming language understanding generalization capabilities of language models. As part of the full dataset, we introduce a new, manually curated subset StatCodeSearch that focuses on R, a popular but so far underrepresented programming language that is often used by researchers outside the field of computer science. For evaluation and comparison, we collect several baseline results using fine-tuned BERT-style models and GPT-style large language models in a zero-shot setting.

cs.CL↗

arXiv2023

Open-World Lifelong Graph Learning

We study the problem of lifelong graph learning in an open-world scenario, where a model needs to deal with new tasks and potentially unknown classes. We utilize Out-of-Distribution (OOD) detection methods to recognize new classes and adapt existing non-graph OOD detection methods to graph data. Crucially, we suggest performing new class detection by combining OOD detection methods with information aggregated from the graph neighborhood. Most OOD detection methods avoid determining a crisp threshold for deciding whether a vertex is OOD. To tackle this problem, we propose a Weakly-supervised Relevance Feedback (Open-WRF) method, which decreases the sensitivity to thresholds in OOD detection. We evaluate our approach on six benchmark datasets. Our results show that the proposed neighborhood aggregation method for OOD scores outperforms existing methods independent of the underlying graph neural network. Furthermore, we demonstrate that our Open-WRF method is more robust to threshold selection and analyze the influence of graph neighborhood on OOD detection. The aggregation and threshold methods are compatible with arbitrary graph neural networks and OOD detection methods, making our approach versatile and applicable to many real-world applications.

cs.LG↗

arXiv2023

Event and Entity Extraction from Generated Video Captions

Annotation of multimedia data by humans is time-consuming and costly, while reliable automatic generation of semantic metadata is a major challenge. We propose a framework to extract semantic metadata from automatically generated video captions. As metadata, we consider entities, the entities' properties, relations between entities, and the video category. We employ two state-of-the-art dense video captioning models with masked transformer (MT) and parallel decoding (PVDC) to generate captions for videos of the ActivityNet Captions dataset. Our experiments show that it is possible to extract entities, their properties, relations between entities, and the video category from the generated captions. We observe that the quality of the extracted information is mainly influenced by the quality of the event localization in the video as well as the performance of the event caption generation.

cs.CV↗

arXiv2023

Transformers are Short Text Classifiers: A Study of Inductive Short Text Classifiers on Benchmarks and Real-world Datasets

Short text classification is a crucial and challenging aspect of Natural Language Processing. For this reason, there are numerous highly specialized short text classifiers. However, in recent short text research, State of the Art (SOTA) methods for traditional text classification, particularly the pure use of Transformers, have been unexploited. In this work, we examine the performance of a variety of short text classifiers as well as the top performing traditional text classifier. We further investigate the effects on two new real-world short text datasets in an effort to address the issue of becoming overly dependent on benchmark datasets with a limited number of characteristics. Our experiments unambiguously demonstrate that Transformers achieve SOTA accuracy on short text classification tasks, raising the question of whether specialized short text techniques are necessary.

cs.CL↗

arXiv2023

Fine-Tuning Language Models for Scientific Writing Support

We support scientific writers in determining whether a written sentence is scientific, to which section it belongs, and suggest paraphrasings to improve the sentence. Firstly, we propose a regression model trained on a corpus of scientific sentences extracted from peer-reviewed scientific papers and non-scientific text to assign a score that indicates the scientificness of a sentence. We investigate the effect of equations and citations on this score to test the model for potential biases. Secondly, we create a mapping of section titles to a standard paper layout in AI and machine learning to classify a sentence to its most likely section. We study the impact of context, i.e., surrounding sentences, on the section classification performance. Finally, we propose a paraphraser, which suggests an alternative for a given sentence that includes word substitutions, additions to the sentence, and structural changes to improve the writing style. We train various large language models on sentences extracted from arXiv papers that were peer reviewed and published at A*, A, B, and C ranked conferences. On the scientificness task, all models achieve an MSE smaller than $2\%$. For the section classification, BERT outperforms WideMLP and SciBERT in most cases. We demonstrate that using context enhances the classification of a sentence, achieving up to a $90\%$ F1-score. Although the paraphrasing models make comparatively few alterations, they produce output sentences close to the gold standard. Large fine-tuned models such as T5 Large perform best in experiments considering various measures of difference between input sentence and gold standard. Code is provided under https://github.com/JustinMuecke/SciSen.

cs.CL↗

arXiv2023

The Split Matters: Flat Minima Methods for Improving the Performance of GNNs

When training a Neural Network, it is optimized using the available training data with the hope that it generalizes well to new or unseen testing data. At the same absolute value, a flat minimum in the loss landscape is presumed to generalize better than a sharp minimum. Methods for determining flat minima have been mostly researched for independent and identically distributed (i. i. d.) data such as images. Graphs are inherently non-i. i. d. since the vertices are edge-connected. We investigate flat minima methods and combinations of those methods for training graph neural networks (GNNs). We use GCN and GAT as well as extend Graph-MLP to work with more layers and larger graphs. We conduct experiments on small and large citation, co-purchase, and protein datasets with different train-test splits in both the transductive and inductive training procedure. Results show that flat minima methods can improve the performance of GNN models by over 2 points, if the train-test split is randomized. Following Shchur et al., randomized splits are essential for a fair evaluation of GNNs, as other (fixed) splits like 'Planetoid' are biased. Overall, we provide important insights for improving and fairly evaluating flat minima methods on GNNs. We recommend practitioners to always use weight averaging techniques, in particular EWA when using early stopping. While weight averaging techniques are only sometimes the best performing method, they are less sensitive to hyperparameters, need no additional training, and keep the original model unchanged. All source code is available in https://github.com/Foisunt/FMMs-in-GNNs.

cs.LG↗

arXiv2023

Computing $k$-Bisimulations for Large Graphs: A Comparison and Efficiency Analysis

Summarizing graphs w.r.t. structural features is important to reduce the graph's size and make tasks like indexing, querying, and visualization feasible. Our generic parallel BRS algorithm efficiently summarizes large graphs w.r.t. a custom equivalence relation $\sim$ defined on the graph's vertices $V$. Moreover, the definition of $\sim$ can be chained $k\geq 1$ times, so the defined equivalence relation becomes a $k$-bisimulation. We evaluate the runtime and memory performance of the BRS algorithm for $k$-bisimulation with $k=1,\ldots,10$ against two algorithms found in the literature (a sequential algorithm due to Kaushik et al. and a parallel algorithm of Schätzle et al.), which we implemented in the same software stack as BRS. We use five real-world and synthetic graph datasets containing 100 million to two billion edges. Our results show that the generic BRS algorithm outperforms the respective native bisimulation algorithms on all datasets for all $k\geq5$ and for smaller $k$ in some cases. The BRS implementations of the two bisimulation algorithms run almost as fast as each other. Thus, the BRS algorithm is an effective parallelization of the sequential Kaushik et al. bisimulation algorithm.

cs.DS↗

arXiv2023

Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes

Lifelong graph learning deals with the problem of continually adapting graph neural network (GNN) models to changes in evolving graphs. We address two critical challenges of lifelong graph learning in this work: dealing with new classes and tackling imbalanced class distributions. The combination of these two challenges is particularly relevant since newly emerging classes typically resemble only a tiny fraction of the data, adding to the already skewed class distribution. We make several contributions: First, we show that the amount of unlabeled data does not influence the results, which is an essential prerequisite for lifelong learning on a sequence of tasks. Second, we experiment with different label rates and show that our methods can perform well with only a tiny fraction of annotated nodes. Third, we propose the gDOC method to detect new classes under the constraint of having an imbalanced class distribution. The critical ingredient is a weighted binary cross-entropy loss function to account for the class imbalance. Moreover, we demonstrate combinations of gDOC with various base GNN models such as GraphSAGE, Simplified Graph Convolution, and Graph Attention Networks. Lastly, our k-neighborhood time difference measure provably normalizes the temporal changes across different graph datasets. With extensive experimentation, we find that the proposed gDOC method is consistently better than a naive adaption of DOC to graphs. Specifically, in experiments using the smallest history size, the out-of-distribution detection score of gDOC is 0.09 compared to 0.01 for DOC. Furthermore, gDOC achieves an Open-F1 score, a combined measure of in-distribution classification and out-of-distribution detection, of 0.33 compared to 0.25 of DOC (32% increase).

cs.LG↗

arXiv2023

Reducing a Set of Regular Expressions and Analyzing Differences of Domain-specific Statistic Reporting

Due to the large amount of daily scientific publications, it is impossible to manually review each one. Therefore, an automatic extraction of key information is desirable. In this paper, we examine STEREO, a tool for extracting statistics from scientific papers using regular expressions. By adapting an existing regular expression inclusion algorithm for our use case, we decrease the number of regular expressions used in STEREO by about $33.8\%$. We reveal common patterns from the condensed rule set that can be used for the creation of new rules. We also apply STEREO, which was previously trained in the life-sciences and medical domain, to a new scientific domain, namely Human-Computer-Interaction (HCI), and re-evaluate it. According to our research, statistics in the HCI domain are similar to those in the medical domain, although a higher percentage of APA-conform statistics were found in the HCI domain. Additionally, we compare extraction on PDF and LaTeX source files, finding LaTeX to be more reliable for extraction.

cs.DL↗

arXiv2022

Graph Summarization with Graph Neural Networks

The goal of graph summarization is to represent large graphs in a structured and compact way. A graph summary based on equivalence classes preserves pre-defined features of a graph's vertex within a $k$-hop neighborhood such as the vertex labels and edge labels. Based on these neighborhood characteristics, the vertex is assigned to an equivalence class. The calculation of the assigned equivalence class must be a permutation invariant operation on the pre-defined features. This is achieved by sorting on the feature values, e. g., the edge labels, which is computationally expensive, and subsequently hashing the result. Graph Neural Networks (GNN) fulfill the permutation invariance requirement. We formulate the problem of graph summarization as a subgraph classification task on the root vertex of the $k$-hop neighborhood. We adapt different GNN architectures, both based on the popular message-passing protocol and alternative approaches, to perform the structural graph summarization task. We compare different GNNs with a standard multi-layer perceptron (MLP) and Bloom filter as non-neural method. For our experiments, we consider four popular graph summary models on a large web graph. This resembles challenging multi-class vertex classification tasks with the numbers of classes ranging from $576$ to multiple hundreds of thousands. Our results show that the performance of GNNs are close to each other. In three out of four experiments, the non-message-passing GraphMLP model outperforms the other GNNs. The performance of the standard MLP is extraordinary good, especially in the presence of many classes. Finally, the Bloom filter outperforms all neural architectures by a large margin, except for the dataset with the fewest number of $576$ classes.

cs.LG↗

arXiv2022

STEREO: A Pipeline for Extracting Experiment Statistics, Conditions, and Topics from Scientific Papers

A common writing style for statistical results are the recommendations of the American Psychology Association, known as APA-style. However, in practice, writing styles vary as reports are not 100% following APA-style or parameters are not reported despite being mandatory. In addition, the statistics are not reported in isolation but in context of experimental conditions investigated and the general topic. We address these challenges by proposing a flexible pipeline STEREO based on active wrapper induction and unsupervised aspect extraction. We applied our pipeline to the over 100,000 documents in the CORD-19 dataset. It required only 0.25% of the corpus (about 500 documents) to learn statistics extraction rules that cover 95% of the sentences in CORD-19. The statistic extraction has nearly 100% precision on APA-conform and 95% precision on non-APA writing styles. In total, we were able to extract 113k reported statistics, of which only <1% is APA conform. We could extract in 46% the correct conditions from APA-conform reports (30% for non-APA). The best model for topic extraction achieves a precision of 75% on statistics reported in APA style (73% for non-APA conform). We conclude that STEREO is a good foundation for automatic statistic extraction and future developments for scientific paper analysis. Particularly the extraction of non-APA conform reports is important and allows applications such as giving feedback to authors about what is missing and could be changed.

cs.DL↗

arXiv2022

rx-anon -- A Novel Approach on the De-Identification of Heterogeneous Data based on a Modified Mondrian Algorithm

Traditional approaches for data anonymization consider relational data and textual data independently. We propose rx-anon, an anonymization approach for heterogeneous semi-structured documents composed of relational and textual attributes. We map sensitive terms extracted from the text to the structured data. This allows us to use concepts like k-anonymity to generate a joined, privacy-preserved version of the heterogeneous data input. We introduce the concept of redundant sensitive information to consistently anonymize the heterogeneous data. To control the influence of anonymization over unstructured textual data versus structured data attributes, we introduce a modified, parameterized Mondrian algorithm. The parameter $λ$ allows to give different weight on the relational and textual attributes during the anonymization process. We evaluate our approach with two real-world datasets using a Normalized Certainty Penalty score, adapted to the problem of jointly anonymizing relational and textual data. The results show that our approach is capable of reducing information loss by using the tuning parameter to control the Mondrian partitioning while guaranteeing k-anonymity for relational attributes as well as for sensitive terms. As rx-anon is a framework approach, it can be reused and extended by other anonymization algorithms, privacy models, and textual similarity metrics.

cs.LG↗