Search Results for author: C. Bayan Bruss

Found 18 papers, 5 papers with code

Simplifying Neural Network Training Under Class Imbalance

1 code implementation NeurIPS 2023 Ravid Shwartz-Ziv, Micah Goldblum, Yucen Lily Li, C. Bayan Bruss, Andrew Gordon Wilson

Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models.

Data Augmentation

From Explanation to Action: An End-to-End Human-in-the-loop Framework for Anomaly Reasoning and Management

no code implementations6 Apr 2023 Xueying Ding, Nikita Seleznev, Senthil Kumar, C. Bayan Bruss, Leman Akoglu

Anomalies are often indicators of malfunction or inefficiency in various systems such as manufacturing, healthcare, finance, surveillance, to name a few.

Anomaly Detection Management

Transfer Learning with Deep Tabular Models

1 code implementation30 Jun 2022 Roman Levin, Valeriia Cherepanova, Avi Schwarzschild, Arpit Bansal, C. Bayan Bruss, Tom Goldstein, Andrew Gordon Wilson, Micah Goldblum

In this work, we demonstrate that upstream data gives tabular neural networks a decisive advantage over widely used GBDT models.

Medical Diagnosis Transfer Learning

Counterfactual Explanations via Latent Space Projection and Interpolation

no code implementations2 Dec 2021 Brian Barr, Matthew R. Harrington, Samuel Sharpe, C. Bayan Bruss

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.

Binary Classification counterfactual

Multi-Domain Self-Supervised Learning

no code implementations29 Sep 2021 Neha Mukund Kalibhat, Yogesh Balaji, C. Bayan Bruss, Soheil Feizi

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.

Contrastive Learning Representation Learning +1

Latent-CF: A Simple Baseline for Reverse Counterfactual Explanations

no code implementations16 Dec 2020 Rachana Balasubramanian, Samuel Sharpe, Brian Barr, Jason Wittenbach, C. Bayan Bruss

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.

counterfactual Fairness

DLGNet-Task: An End-to-end Neural Network Framework for Modeling Multi-turn Multi-domain Task-Oriented Dialogue

no code implementations4 Oct 2020 Oluwatobi O. Olabiyi, Prarthana Bhattarai, C. Bayan Bruss, Zachary Kulis

Task oriented dialogue (TOD) requires the complex interleaving of a number of individually controllable components with strong guarantees for explainability and verifiability.

Dialogue Generation Natural Language Understanding

Machine Learning for Temporal Data in Finance: Challenges and Opportunities

no code implementations11 Sep 2020 Jason Wittenbach, Brian d'Alessandro, C. Bayan Bruss

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.

BIG-bench Machine Learning Time Series Analysis

Towards Ground Truth Explainability on Tabular Data

1 code implementation20 Jul 2020 Brian Barr, Ke Xu, Claudio Silva, Enrico Bertini, Robert Reilly, C. Bayan Bruss, Jason D. Wittenbach

In data science, there is a long history of using synthetic data for method development, feature selection and feature engineering.

Feature Engineering feature selection

Navigating the Dynamics of Financial Embeddings over Time

no code implementations1 Jul 2020 Antonia Gogoglou, Brian Nguyen, Alan Salimov, Jonathan Rider, C. Bayan Bruss

Financial transactions constitute connections between entities and through these connections a large scale heterogeneous weighted graph is formulated.

Graph Representation Learning

Quantifying Challenges in the Application of Graph Representation Learning

no code implementations18 Jun 2020 Antonia Gogoglou, C. Bayan Bruss, Brian Nguyen, Reza Sarshogh, Keegan E. Hines

Graph Representation Learning (GRL) has experienced significant progress as a means to extract structural information in a meaningful way for subsequent learning tasks.

Graph Representation Learning Link Prediction +1

On the Interpretability and Evaluation of Graph Representation Learning

no code implementations7 Oct 2019 Antonia Gogoglou, C. Bayan Bruss, Keegan E. Hines

With the rising interest in graph representation learning, a variety of approaches have been proposed to effectively capture a graph's properties.

Graph Representation Learning

DeepTrax: Embedding Graphs of Financial Transactions

no code implementations16 Jul 2019 C. Bayan Bruss, Anish Khazane, Jonathan Rider, Richard Serpe, Antonia Gogoglou, Keegan E. Hines

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.

BIG-bench Machine Learning Fraud Detection +4

Graph Embeddings at Scale

no code implementations3 Jul 2019 C. Bayan Bruss, Anish Khazane, Jonathan Rider, Richard Serpe, Saurabh Nagrecha, Keegan E. Hines

Graph embedding is a popular algorithmic approach for creating vector representations for individual vertices in networks.

Graph Embedding graph partitioning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.