Search Results for author:
Found 13 papers, 1 papers with code
Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection
We propose framing toxicity detection as multi-task learning (MTL), allowing a model to specialize on the relationships that are relevant to each demographic group while also leveraging shared properties across groups.
Fairly Accurate: Learning Optimal Accuracy vs. Fairness Tradeoffs for Hate Speech Detection
In this work, we first introduce a differentiable measure that enables direct optimization of group fairness (specifically, balancing accuracy across groups) in model training.
Scalable Unidirectional Pareto Optimality for Multi-Task Learning with Constraints
Multi-objective optimization (MOO) problems require balancing competing objectives, often under constraints.
Range-Net: A High Precision Neural SVD
For Big Data applications, computing a rank-$r$ Singular Value Decomposition (SVD) is restrictive due to the main memory requirements.
A Two-Stage Neural-Filter Pareto Front Extractor and the need for Benchmarking
The Stage-1 neural network efficiently extracts the \textit{weak} Pareto front, using Fritz-John Conditions (FJC) as the discriminator, with no assumptions of convexity on the objectives or constraints.
Tail-Net: Extracting Lowest Singular Triplets for Big Data Applications
However, a number of applications such as community detection, clustering, or bottleneck identification in large scale graph data-sets rely upon identifying the lowest singular values and the singular corresponding vectors.
SCA-Net: A Self-Correcting Two-Layer Autoencoder for Hyper-spectral Unmixing
We show for the first time that a two-layer autoencoder (SCA), with $2FK$ parameters ($F$ features, $K$ endmembers), achieves error metrics that are scales apart ($10^{-5})$ from previously reported values $(10^{-2})$.
A Hybrid 2-stage Neural Optimization for Pareto Front Extraction
The first stage (neural network) efficiently extracts a weak Pareto front, using Fritz-John conditions as the discriminator, with no assumptions of convexity on the objectives or constraints.
Range-Net: A High Precision Streaming SVD for Big Data Applications
Although these methods are claimed to be applicable to scientific computations due to associated tail-energy error bounds, the approximation errors in the singular vectors and values are high when the aforementioned assumption does not hold.
Extracting Optimal Solution Manifolds using Constrained Neural Optimization
However, such an approach is often restricted to a strict class of functions, deviation from which results in sub-optimal solution to the original problem.
Prevention is Better than Cure: Handling Basis Collapse and Transparency in Dense Networks
We demonstrate through carefully chosen numerical experiments that the basis collapse issue leads to the design of massively redundant networks.
TIME: A Transparent, Interpretable, Model-Adaptive and Explainable Neural Network for Dynamic Physical Processes
Partial Differential Equations are infinite dimensional encoded representations of physical processes.
Higher Order Mutual Information Approximation for Feature Selection
Feature selection is a process of choosing a subset of relevant features so that the quality of prediction models can be improved.
