Search Results for author:
Found 56 papers, 24 papers with code
Emergent Abilities in Large Language Models: A Survey
The scaling of these models, accomplished by increasing the number of parameters and the magnitude of the training datasets, has been linked to various so-called emergent abilities that were previously unobserved.
TLOB: A Novel Transformer Model with Dual Attention for Stock Price Trend Prediction with Limit Order Book Data
Stock Price Trend Prediction (SPTP) based on Limit Order Book (LOB) data is a fundamental challenge in financial markets.
RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting
Compared with unsupervised SoTA models, RAZOR improves by 3. 5% on the FEVER and 6. 5% on MNLI and SNLI datasets according to the F1 score.
Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers
This study provides a structured approach to embedding-based feature enrichment and illustrates its benefits in ensemble learning for tabular data.
Understanding Knowledge Drift in LLMs through Misinformation
Our experiments reveal that an LLM's uncertainty can increase up to 56. 6% when the question is answered incorrectly due to the exposure to false information.
Enhancing Fairness through Reweighting: A Path to Attain the Sufficiency Rule
We introduce an innovative approach to enhancing the empirical risk minimization (ERM) process in model training through a refined reweighting scheme of the training data to enhance fairness.
The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AI
Psychological trauma can manifest following various distressing events and is captured in diverse online contexts.
GermanPartiesQA: Benchmarking Commercial Large Language Models for Political Bias and Sycophancy
LLMs are changing the way humans create and interact with content, potentially affecting citizens' political opinions and voting decisions.
P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Models
A multitude of industries depend on accurate and reasonable tabular data augmentation for their business processes.
Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers
We address the critical challenge of applying feature attribution methods to the transformer architecture, which dominates current applications in natural language processing and beyond.
Towards Non-Adversarial Algorithmic Recourse
We subsequently investigate how different components in the objective functions, e. g., the machine learning model or cost function used to measure distance, determine whether the outcome can be considered an adversarial example or not.
Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization
This research significantly reduces training costs of proximal policy-guided models and demonstrates the potential for self-correction of language models.
Taking the Next Step with Generative Artificial Intelligence: The Transformative Role of Multimodal Large Language Models in Science Education
The integration of Artificial Intelligence (AI), particularly Large Language Model (LLM)-based systems, in education has shown promise in enhancing teaching and learning experiences.
Adversarial Reweighting Guided by Wasserstein Distance for Bias Mitigation
To balance the data distribution between the majority and the minority groups, our approach deemphasizes samples from the majority group.
Causal Fairness-Guided Dataset Reweighting using Neural Networks
The two neural networks can approximate the causal model of the data, and the causal model of interventions.
Counterfactual Explanation for Regression via Disentanglement in Latent Space
In this paper, we introduce a novel method to generate CEs for a pre-trained regressor by first disentangling the label-relevant from the label-irrelevant dimensions in the latent space.
Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapes
The GAEs minimise the reconstruction error between the original graph and its learned representation during training.
Counterfactual Explanation via Search in Gaussian Mixture Distributed Latent Space
In this paper, we introduce a new method to generate CEs for a pre-trained binary classifier by first shaping the latent space of an autoencoder to be a mixture of Gaussian distributions.
Gaussian Membership Inference Privacy
In particular, we derive a parametric family of $f$-MIP guarantees that we refer to as $\mu$-Gaussian Membership Inference Privacy ($\mu$-GMIP) by theoretically analyzing likelihood ratio-based membership inference attacks on stochastic gradient descent (SGD).
Explanation Shift: How Did the Distribution Shift Impact the Model?
Then, state-of-the-art techniques model input data distributions or model prediction distributions and try to understand issues regarding the interactions between learned models and shifting distributions.
Relational Local Explanations
The majority of existing post-hoc explanation approaches for machine learning models produce independent, per-variable feature attribution scores, ignoring a critical inherent characteristics of homogeneously structured data, such as visual or text data: there exist latent inter-variable relationships between features.
Entry Dependent Expert Selection in Distributed Gaussian Processes Using Multilabel Classification
Ensemble methods aggregate models' predictions by assuming a perfect diversity of local predictors.
Decomposing Counterfactual Explanations for Consequential Decision Making
In this work, we develop \texttt{DEAR} (DisEntangling Algorithmic Recourse), a novel and practical recourse framework that bridges the gap between the IMF and the strong causal assumptions.
I Prefer not to Say: Protecting User Consent in Models with Optional Personal Data
In this work, we show that the decision not to share data can be considered as information in itself that should be protected to respect users' privacy.
Explanation Shift: Detecting distribution shifts on tabular data via the explanation space
We provide a mathematical analysis of different types of distribution shifts as well as synthetic experimental examples.
Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
A better understanding of the needs of XAI users, as well as human-centered evaluations of explainable models are both a necessity and a challenge.
Explainable Artificial Intelligence (XAI)
Explainable Models
+3
Language Models are Realistic Tabular Data Generators
Tabular data is among the oldest and most ubiquitous forms of data.
Ranked #1 on
Tabular Data Generation
on HELOC
Change Detection for Local Explainability in Evolving Data Streams
In particular, we show that local attributions can become obsolete each time the predictive model is updated or concept drift alters the data generating distribution.
On the Trade-Off between Actionable Explanations and the Right to be Forgotten
Thus, our work raises fundamental questions about the compatibility of "the right to an actionable explanation" in the context of the "right to be forgotten", while also providing constructive insights on the determining factors of recourse robustness.
BoxShrink: From Bounding Boxes to Segmentation Masks
One of the core challenges facing the medical image computing community is fast and efficient data sample labeling.
When are Post-hoc Conceptual Explanations Identifiable?
Interest in understanding and factorizing learned embedding spaces through conceptual explanations is steadily growing.
Standardized Evaluation of Machine Learning Methods for Evolving Data Streams
In this sense, we hope that our work will contribute to more standardized, reliable and realistic testing and comparison of online machine learning methods.
Dynamic Model Tree for Interpretable Data Stream Learning
Dynamic Model Trees are thus a powerful online learning framework that contributes to more lightweight and interpretable machine learning in data streams.
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse
To this end, we propose a novel objective function which simultaneously minimizes the gap between the achieved (resulting) and desired recourse invalidation rates, minimizes recourse costs, and also ensures that the resulting recourse achieves a positive model prediction.
Gaussian Graphical Models as an Ensemble Method for Distributed Gaussian Processes
Distributed Gaussian process (DGP) is a popular approach to scale GP to big data which divides the training data into some subsets, performs local inference for each partition, and aggregates the results to acquire global prediction.
A Consistent and Efficient Evaluation Strategy for Attribution Methods
With a variety of local feature attribution methods being proposed in recent years, follow-up work suggested several evaluation strategies.
A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines
Understanding the results of deep neural networks is an essential step towards wider acceptance of deep learning algorithms.
Deep Neural Networks and Tabular Data: A Survey
Moreover, we discuss deep learning approaches for generating tabular data, and we also provide an overview over strategies for explaining deep models on tabular data.
CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
In summary, our work provides the following contributions: (i) an extensive benchmark of 11 popular counterfactual explanation methods, (ii) a benchmarking framework for research on future counterfactual explanation methods, and (iii) a standardized set of integrated evaluation measures and data sets for transparent and extensive comparisons of these methods.
TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types
The data set includes 2D and 3D landmarks, semantic segmentation, 3D eyeball annotation and the gaze vector and eye movement types for all images.
Gaussian Experts Selection using Graphical Models
Imposing the \emph{conditional independence assumption} (CI) between the experts renders the aggregation of different expert predictions time efficient at the cost of poor uncertainty quantification.
On Baselines for Local Feature Attributions
Our experimental study illustrates the sensitivity of popular attribution models to the baseline, thus laying the foundation for a more in-depth discussion on sensible baseline methods for tabular data.
Lessons Learned from the 1st ARIEL Machine Learning Challenge: Correcting Transiting Exoplanet Light Curves for Stellar Spots
For instance, the most prolific method for detecting exoplanets and inferring several of their characteristics, transit photometry, is very sensitive to the presence of stellar spots.
Learning Parameter Distributions to Detect Concept Drift in Data Streams
By treating the parameters of a predictive model as random variables, we show that concept drift corresponds to a change in the distribution of optimal parameters.
Aggregating Dependent Gaussian Experts in Local Approximation
The precision matrix encodes conditional dependencies between experts and is used to detect strongly dependent experts and construct an improved aggregation.
On Counterfactual Explanations under Predictive Multiplicity
In this work, we derive a general upper bound for the costs of counterfactual explanations under predictive multiplicity.
Leveraging Model Inherent Variable Importance for Stable Online Feature Selection
Feature selection can be a crucial factor in obtaining robust and accurate predictions.
Learning Model-Agnostic Counterfactual Explanations for Tabular Data
On one hand, we suggest to complement the catalogue of counterfactual quality measures [1] using a criterion to quantify the degree of difficulty for a certain counterfactual suggestion.
Training Decision Trees as Replacement for Convolution Layers
Our approach reduces the complexity of convolutions by replacing it with binary decisions.
A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees
We propose shallow model trees as a way to combine simple and highly transparent predictive models for higher predictive power without losing the transparency of the original models.
Combining Restricted Boltzmann Machines with Neural Networks for Latent Truth Discovery
Latent truth discovery, LTD for short, refers to the problem of aggregating ltiple claims from various sources in order to estimate the plausibility of atements about entities.
Restricted Boltzmann Machines for Robust and Fast Latent Truth Discovery
Despite a multitude of algorithms to address the LTD problem that can be found in literature, only little is known about their overall performance with respect to effectiveness (in terms of truth discovery capabilities), efficiency and robustness.
PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection
Real-time, accurate, and robust pupil detection is an essential prerequisite for pervasive video-based eye-tracking.
PupilNet: Convolutional Neural Networks for Robust Pupil Detection
Real-time, accurate, and robust pupil detection is an essential prerequisite for pervasive video-based eye-tracking.
SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases
The Internet has enabled the creation of a growing number of large-scale knowledge bases in a variety of domains containing complementary information.
