Search Results for author:
Found 21 papers, 6 papers with code
Explain What You Mean: Intent Augmented Knowledge Graph Recommender Built With An LLM
Interaction sparsity is a long-standing challenge in recommendation systems.
A Simple Baseline for Predicting Events with Auto-Regressive Tabular Transformers
Moreover, these approaches often assume specific use-cases, for example that we know the labels of all historic events or that we only predict a pre-specified label and not the data's features themselves.
Just How Flexible are Neural Networks in Practice?
Our findings indicate that: (1) standard optimizers find minima where the model can only fit training sets with significantly fewer samples than it has parameters; (2) convolutional networks are more parameter-efficient than MLPs and ViTs, even on randomly labeled data; (3) while stochastic training is thought to have a regularizing effect, SGD actually finds minima that fit more training data than full-batch gradient descent; (4) the difference in capacity to fit correctly labeled and incorrectly labeled samples can be predictive of generalization; (5) ReLU activation functions result in finding minima that fit more data despite being designed to avoid vanishing and exploding gradients in deep architectures.
Simplifying Neural Network Training Under Class Imbalance
Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models.
From Explanation to Action: An End-to-End Human-in-the-loop Framework for Anomaly Reasoning and Management
Anomalies are often indicators of malfunction or inefficiency in various systems such as manufacturing, healthcare, finance, surveillance, to name a few.
BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence
By perturbing the input variables in rank order of importance, the goal is to assess the sensitivity of the model's performance.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Transfer Learning with Deep Tabular Models
In this work, we demonstrate that upstream data gives tabular neural networks a decisive advantage over widely used GBDT models.
Counterfactual Explanations via Latent Space Projection and Interpolation
Counterfactual explanations represent the minimal change to a data sample that alters its predicted classification, typically from an unfavorable initial class to a desired target class.
Multi-Domain Self-Supervised Learning
In fact, training these methods on a combination of several domains often degrades the quality of learned representations compared to the models trained on a single domain.
MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data
Class-imbalanced data, in which some classes contain far more samples than others, is ubiquitous in real-world applications.
SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
We devise a hybrid deep learning approach to solving tabular data problems.
Latent-CF: A Simple Baseline for Reverse Counterfactual Explanations
In the environment of fair lending laws and the General Data Protection Regulation (GDPR), the ability to explain a model's prediction is of paramount importance.
DLGNet-Task: An End-to-end Neural Network Framework for Modeling Multi-turn Multi-domain Task-Oriented Dialogue
Task oriented dialogue (TOD) requires the complex interleaving of a number of individually controllable components with strong guarantees for explainability and verifiability.
Machine Learning for Temporal Data in Finance: Challenges and Opportunities
Temporal data are ubiquitous in the financial services (FS) industry -- traditional data like economic indicators, operational data such as bank account transactions, and modern data sources like website clickstreams -- all of these occur as a time-indexed sequence.
Towards Ground Truth Explainability on Tabular Data
In data science, there is a long history of using synthetic data for method development, feature selection and feature engineering.
Navigating the Dynamics of Financial Embeddings over Time
Financial transactions constitute connections between entities and through these connections a large scale heterogeneous weighted graph is formulated.
Quantifying Challenges in the Application of Graph Representation Learning
Graph Representation Learning (GRL) has experienced significant progress as a means to extract structural information in a meaningful way for subsequent learning tasks.
On the Interpretability and Evaluation of Graph Representation Learning
With the rising interest in graph representation learning, a variety of approaches have been proposed to effectively capture a graph's properties.
Towards Automated Machine Learning: Evaluation and Comparison of AutoML Approaches and Tools
There has been considerable growth and interest in industrial applications of machine learning (ML) in recent years.
DeepTrax: Embedding Graphs of Financial Transactions
In this paper, we present a novel application of representation learning to bipartite graphs of credit card transactions in order to learn embeddings of account and merchant entities.
Graph Embeddings at Scale
Graph embedding is a popular algorithmic approach for creating vector representations for individual vertices in networks.
