Vassilis Christophides

Improving the quality of training samples is crucial for improving the reliability and performance of ML models. In this paper, we conduct a comparative evaluation of influence-based signals for debugging training data. These signals can potentially identify both mislabeled and anomalous samples from a potentially noisy training set as we build the models and hence alleviate the need for dedicated glitch detectors. Although several influence-based signals (e.g., Self-Influence, Average Absolute Influence, Marginal Influence, GD-class) have been recently proposed in the literature, there are no experimental studies for assessing their power in detecting different glitch types (e.g., mislabeled and anomalous samples) under a common influence estimator (e.g., TraceIn) for different data modalities (image and tabular), and deep learning models (trained from scratch or foundation). Through extensive experiments, we show that signals like Self-Influence effectively detect mislabeled samples, but none of the existing signals can detect anomalies. Existing signals do not take into account the training dynamics, i.e., how the samples' influence on the model changes during training, while some signals fall into influence cancellation effects, i.e., influence score is zero due to unsigned scores accumulation, resulting in misleading influence attribution.

Numerous real-world data contain missing values, while in contrast, most Machine Learning (ML) algorithms assume complete datasets. For this reason, several imputation algorithms have been proposed to predict and fill in the missing values. Given the advances in predictive modeling algorithms tuned in an Automated Machine Learning context (AutoML) setting, a question that naturally arises is to what extent sophisticated imputation algorithms (e.g., Neural Network based) are really needed, or we can obtain a descent performance using simple methods like Mean/Mode (MM). In this article, we experimentally compare six state-of-the-art representatives of different imputation algorithmic families from an AutoML predictive modeling perspective, including a feature selection step and combined algorithm and hyper-parameter selection. We used a commercial AutoML tool for our experiments, in which we included the selected imputation methods. Experiments ran on 25 binary classification real-world incomplete datasets with missing values and 10 binary classification complete datasets in which synthetic missing values are introduced according to different missingness mechanisms, at varying missing frequencies. The main conclusion drawn from our experiments is that the best method on average is the Denoise AutoEncoder on real-world datasets and the MissForest in simulated datasets, followed closely by MM. In addition, binary indicator variables encoding missingness patterns actually improve predictive performance, on average. Last, although there are cases where Neural-Network-based imputation significantly improves predictive performance, this comes at a great computational cost and requires measuring all feature values to impute new samples.

In recent years, we have witnessed the proliferation of knowledge graphs (KG) in various domains, aiming to support applications like question answering, recommendations, etc. A frequent task when integrating knowledge from different KGs is to find which subgraphs refer to the same real-world entity, a task largely known as the Entity Alignment. Recently, embedding methods have been used for entity alignment tasks, that learn a vector-space representation of entities which preserves their similarity in the original KGs. A wide variety of supervised, unsupervised, and semi-supervised methods have been proposed that exploit both factual (attribute based) and structural information (relation based) of entities in the KGs. Still, a quantitative assessment of their strengths and weaknesses in real-world KGs according to different performance metrics and KG characteristics is missing from the literature. In this work, we conduct the first meta-level analysis of popular embedding methods for entity alignment, based on a statistically sound methodology. Our analysis reveals statistically significant correlations of different embedding methods with various meta-features extracted by KGs and rank them in a statistically significant way according to their effectiveness across all real-world KGs of our testbed. Finally, we study interesting trade-offs in terms of methods’ effectiveness and efficiency.

In recent years, we have witnessed the proliferation of knowledge graphs (KG) in various domains, aiming to support applications like question answering, recommendations, etc. A frequent task when integrating knowledge from different KGs is to find which subgraphs refer to the same real-world entity. Recently, embedding methods have been used for entity alignment tasks, that learn a vector-space representation of entities which preserves their similarity in the original KGs. A wide variety of supervised, unsupervised, and semi-supervised methods have been proposed that exploit both factual (attribute based) and structural information (relation based) of entities in the KGs. Still, a quantitative assessment of their strengths and weaknesses in real-world KGs according to different performance metrics and KG characteristics is missing from the literature. In this work, we conduct the first meta-level analysis of popular embedding methods for entity alignment, based on a statistically sound methodology. Our analysis reveals statistically significant correlations of different embedding methods with various meta-features extracted by KGs and rank them in a statistically significant way according to their effectiveness across all real-world KGs of our testbed. Finally, we study interesting trade-offs in terms of methods' effectiveness and efficiency.