@unpublished{graffeuille2024lake,

title = {Lake by Lake, Globally: Enhancing Water Quality Remote Sensing with Multi-Task Learning Models},

author = {Olivier Graffeuille and Moritz Lehmann and Matthew Allan and J\"{o}rg Wicker and Yun Sing Koh },

doi = {10.2139/ssrn.4762429},

issn = {1556-5068},

year  = {2024},

date = {2024-03-17},

abstract = {The estimation of water quality from satellite remote sensing data in inland and coastal waters is an important yet challenging problem. Recent collaborative efforts have produced large global datasets with sufficient data to train machine learning models with high accuracy. In this work, we investigate global water quality remote sensing models at the granularity of individual water bodies. We introduce Multi-Task Learning (MTL), a machine learning technique that learns a distinct model for each water body in the dataset from few data points by sharing knowledge between models. This approach allows MTL to learn water body differences, leading to more accurate predictions. We train and validate our model on the GLORIA dataset of in situ measured remote sensing reflectance and three water quality indicators: chlorophyll$a$, total suspended solids and coloured dissolved organic matter. MTL outperforms other machine learning models by 8-31% in Root Mean Squared Error (RMSE) and 12-34% in Mean Absolute Percentage Error (MAPE). Training on a smaller dataset of chlorophyll$a$ measurements from New Zealand lakes with simultaneous Sentinel-3 OLCI remote sensing reflectance further demonstrates the effectiveness of our model when applied regionally. Additionally, we investigate the performance of machine learning models at estimating the variation in water quality indicators within individual water bodies. Our results reveal that overall performance metrics overestimate the quality of model fit of models trained on a large number of water bodies due to the large between-water body variability of water quality indicators. In our experiments, when estimating TSS or CDOM, all models excluding multi-task learning fail to learn within-water body variability, and fail to outperform a naive baseline approach, suggesting that these models may be of limited usefulness to practitioners monitoring water quality. Overall, our research highlights the importance of considering water body differences in water quality remote sensing research for both model design and evaluation. },

keywords = {},

pubstate = {forthcoming},

tppubtype = {unpublished}

}

@unpublished{lyu2023regional,

title = {Regional Bias in Monolingual English Language Models},

author = {Jiachen Lyu and Katharina Dost and Yun Sing Koh and J\"{o}rg Wicker},

doi = {10.21203/rs.3.rs-3713494/v1},

year  = {2023},

date = {2023-12-06},

urldate = {2023-12-06},

abstract = {In Natural Language Processing (NLP), pre-trained language models (LLMs) are widely employed and refined for various tasks. These models have shown considerable social and geographic biases creating skewed or even unfair representations of certain groups. Research focuses on biases toward L2 (English as a second language) regions but neglects bias within L1 (first language) regions. In this work, we ask if there is regional bias within L1 regions already inherent in pre-trained LLMs and, if so, what the consequences are in terms of downstream model performance. We contribute an investigation framework specifically tailored for low-resource regions, offering a method to identify bias without imposing strict requirements for labeled datasets. Our research reveals subtle geographic variations in the word embeddings of BERT, even in cultures traditionally perceived as similar. These nuanced features, once captured, have the potential to significantly impact downstream tasks. Generally, models exhibit comparable performance on datasets that share similarities, and conversely, performance may diverge when datasets differ in their nuanced features embedded within the language. It is crucial to note that estimating model performance solely based on standard benchmark datasets may not necessarily apply to the datasets with distinct features from the benchmark datasets. Our proposed framework plays a pivotal role in identifying and addressing biases detected in word embeddings, particularly evident in low-resource regions such as New Zealand.},

keywords = {},

pubstate = {forthcoming},

tppubtype = {unpublished}

}

@unpublished{hua2023systematic,

title = {A Systematic Review of Aspect-based Sentiment Analysis: Domains, Methods, and Trends},

author = {Yan Cathy Hua and Paul Denny and J\"{o}rg Wicker and Katerina Taskova},

url = {https://arxiv.org/abs/2311.10777},

doi = {10.48550/arXiv.2311.10777},

year  = {2023},

date = {2023-11-17},

urldate = {2023-11-17},

abstract = {Aspect-based Sentiment Analysis (ABSA) is a fine-grained type of sentiment analysis that identifies aspects and their associated opinions from a given text. With the surge of digital opinionated text data, ABSA gained increasing popularity for its ability to mine more detailed and targeted insights. Many review papers on ABSA subtasks and solution methodologies exist, however, few focus on trends over time or systemic issues relating to research application domains, datasets, and solution approaches. To fill the gap, this paper presents a Systematic Literature Review (SLR) of ABSA studies with a focus on trends and high-level relationships among these fundamental components. This review is one of the largest SLRs on ABSA, and also, to our knowledge, the first that systematically examines the trends and inter-relations among ABSA research and data distribution across domains and solution paradigms and approaches. Our sample includes 519 primary studies screened from 4191 search results without time constraints via an innovative automatic filtering process. Our quantitative analysis not only identifies trends in nearly two decades of ABSA research development but also unveils a systemic lack of dataset and domain diversity as well as domain mismatch that may hinder the development of future ABSA research. We discuss these findings and their implications and propose suggestions for future research. },

keywords = {},

pubstate = {forthcoming},

tppubtype = {unpublished}

}

@unpublished{dost2023defining,

title = {Defining Applicability Domain in Biodegradation Pathway Prediction},

author = {Katharina Dost and Jason Tam and Tim Lorsbach and Sebastian Schmidt and J\"{o}rg Wicker},

doi = {https://doi.org/10.21203/rs.3.rs-3587632/v1},

year  = {2023},

date = {2023-11-10},

urldate = {2023-11-10},

abstract = {When developing a new chemical, investigating its long-term influences on the environment is crucial to prevent harm. Unfortunately, these experiments are time-consuming. In silico methods can learn from already obtained data to predict biotransformation pathways, and thereby help focus all development efforts on only the most promising chemicals. As all data-based models, these predictors will output pathway predictions for all input compounds in a suitable format, however, these predictions will be faulty unless the model has seen similar compounds during the training process. A common approach to prevent this for other types of models is to define an Applicability Domain for the model that makes predictions only for in-domain compounds and rejects out-of-domain ones. Nonetheless, although exploration of the compound space is particularly interesting in the development of new chemicals, no Applicability Domain method has been tailored to the specific data structure of pathway predictions yet. In this paper, we are the first to define Applicability Domain specialized in biodegradation pathway prediction. Assessing a model’s reliability from different angles, we suggest a three-stage approach that checks for applicability, reliability, and decidability of the model for a queried compound and only allows it to output a prediction if all three stages are passed. Experiments confirm that our proposed technique reliably rejects unsuitable compounds and therefore improves the safety of the biotransformation pathway predictor. },

keywords = {},

pubstate = {forthcoming},

tppubtype = {unpublished}

}

@unpublished{nokey,

title = {Advancements in Biotransformation Pathway Prediction: Enhancements, Datasets, and Novel Functionalities in enviPath},

author = {Jasmin Hafner and Tim Lorsbach and Sebastian Schmidt and Liam Brydon and Katharina Dost and Kunyang Zhang and Kathrin Fenner and J\"{o}rg Wicker},

doi = {10.21203/rs.3.rs-3607847/v1},

year  = {2023},

date = {2023-11-03},

urldate = {2023-11-03},

abstract = {enviPath is a widely used database and prediction system for microbial biotransformation pathways of primarily xenobiotic compounds. Data and prediction system are freely available both via a web interface and a public REST API.  Since its initial release in 2016, we extended the data available in enviPath and improved the performance of the prediction system  and usability of the overall system. We now provide three diverse data sets, covering microbial biotransformation in different environments and under different experimental conditions. This also enabled developing a pathway prediction model that is applicable to a more diverse set of chemicals. In the prediction engine, we implemented a new evaluation tailored towards pathway prediction, that returns a more honest and holistic view on the performance. We also implemented a novel applicability domain algorithm, which allows the user to estimate how well the model will perform on their data. Finally, we improved the implementation to speed up the overall system and provide new functionality via a plugin system. Overall, enviPath has developed into a reliable database and prediction system with a unique use case in research in microbial biotransformations. },

keywords = {},

pubstate = {forthcoming},

tppubtype = {unpublished}

}

@unpublished{Chang2023poison,

title = {Poison is Not Traceless: Fully-Agnostic Detection of Poisoning Attacks },

author = {Xinglong Chang and Katharina Dost and Gillian Dobbie and J\"{o}rg Wicker},

url = {http://arxiv.org/abs/2310.16224},

doi = {10.48550/arXiv.2310.16224},

year  = {2023},

date = {2023-10-23},

urldate = {2023-10-23},

abstract = {The performance of machine learning models depends on the quality of the underlying data. Malicious actors can attack the model by poisoning the training data. Current detectors are tied to either specific data types, models, or attacks, and therefore have limited applicability in real-world scenarios. This paper presents a novel fully-agnostic framework, Diva (Detecting InVisible Attacks), that detects attacks solely relying on analyzing the potentially poisoned data set. Diva is based on the idea that poisoning attacks can be detected by comparing the classifier’s accuracy on poisoned and clean data and pre-trains a meta-learner using Complexity Measures to estimate the otherwise unknown accuracy on a hypothetical clean dataset. The framework applies to generic poisoning attacks. For evaluation purposes, in this paper, we test Diva on label-flipping attacks.},

keywords = {},

pubstate = {forthcoming},

tppubtype = {unpublished}

}

@unpublished{Chang2023fast,

title = {Fast Adversarial Label-Flipping Attack on Tabular Data},

author = {Xinglong Chang and Gillian Dobbie and J\"{o}rg Wicker},

url = {https://arxiv.org/abs/2310.10744},

doi = {10.48550/arXiv.2310.10744},

year  = {2023},

date = {2023-10-16},

urldate = {2023-10-16},

abstract = {Machine learning models are increasingly used in fields that require high reliability such as cybersecurity. However, these models remain vulnerable to various attacks, among which the adversarial label-flipping attack poses significant threats. In label-flipping attacks, the adversary maliciously flips a portion of training labels to compromise the machine learning model. This paper raises significant concerns as these attacks can camouflage a highly skewed dataset as an easily solvable classification problem, often misleading machine learning practitioners into lower defenses and miscalculations of potential risks. This concern amplifies in tabular data settings, where identifying true labels requires expertise, allowing malicious label-flipping attacks to easily slip under the radar. To demonstrate this risk is inherited in the adversary\'s objective, we propose FALFA (Fast Adversarial Label-Flipping Attack), a novel efficient attack for crafting adversarial labels. FALFA is based on transforming the adversary\'s objective and employs linear programming to reduce computational complexity. Using ten real-world tabular datasets, we demonstrate FALFA\'s superior attack potential, highlighting the need for robust defenses against such threats. },

keywords = {},

pubstate = {forthcoming},

tppubtype = {unpublished}

}