research
∙
08/04/2023
Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition
Optical Character Recognition (OCR) enables automatic text extraction fr...
share
research
∙
05/22/2023
Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learning
Molecular representation learning is a crucial task in predicting molecu...
research
∙
04/17/2023
Toward Auto-evaluation with Confidence-based Category Relation-aware Regression
Auto-evaluation aims to automatically evaluate a trained model on any te...
research
∙
04/13/2023
Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution
How to estimate the uncertainty of a given model is a crucial problem. C...
research
∙
02/14/2023
Enhancing Deep Knowledge Tracing with Auxiliary Tasks
Knowledge tracing (KT) is the problem of predicting students' future per...
research
∙
02/14/2023
Improving Interpretability of Deep Sequential Knowledge Tracing Models with Question-centric Cognitive Representations
Knowledge tracing (KT) is a crucial technique to predict students' futur...
research
∙
02/14/2023
simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing
Knowledge tracing (KT) is the problem of predicting students' future per...
research
∙
11/03/2022
Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity
Existing regulations prohibit model developers from accessing protected ...
research
∙
08/13/2022
Finding Point with Image: An End-to-End Benchmark for Vision-based UAV Localization
In the past, image retrieval was the mainstream solution for cross-view ...
research
∙
08/04/2022
Differentially Private Counterfactuals via Functional Mechanism
Counterfactual, serving as one emerging type of model explanation, has a...
research
∙
07/13/2022
Wide Deep Learning for Judging Student Performance in Online One-on-one Math Classes
In this paper, we investigate the opportunities of automating the judgme...
research
∙
06/30/2022
Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations
Deep neural networks (DNNs) have been shown to be vulnerable against adv...
research
∙
06/29/2022
Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale
The success of DNNs is driven by the counter-intuitive ability of over-p...
research
∙
06/24/2022
DialogID: A Dialogic Instruction Dataset for Improving Teaching Effectiveness in Online Environments
Online dialogic instructions are a set of pedagogical instructions used ...
research
∙
06/23/2022
A Design of A Simple Yet Effective Exercise Recommendation System in K-12 Online Learning
We propose a simple but effective method to recommend exercises with hig...
research
∙
06/23/2022
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
Knowledge tracing (KT) is the task of using students' historical learnin...
research
∙
04/07/2022
Characterizing User Behaviors in Open-Source Software User Forums: An Empirical Study
User forums of Open Source Software (OSS) enable end-users to collaborat...
research
∙
03/22/2022
Residual-Guided Non-Intrusive Speech Quality Assessment
This paper proposes an approach to improve Non-Intrusive speech quality ...
research
∙
02/19/2022
The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness
Computer scientists are trained to create abstractions that simplify and...
research
∙
01/24/2022
DuVisor: a User-level Hypervisor Through Delegated Virtualization
Today's mainstream virtualization systems comprise of two cooperative co...
research
∙
11/02/2021
On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Services
Artificial intelligence (AI) continues to find more numerous and more cr...
research
∙
10/06/2021
Adversarial Attacks on Machinery Fault Diagnosis
Despite the great progress of neural network-based (NN-based) machinery ...
research
∙
08/11/2021
Ontology drift is a challenge for explainable data governance
We introduce the needs for explainable AI that arise from Standard No. 2...
research
∙
08/11/2021
Beyond Fairness Metrics: Roadblocks and Challenges for Ethical AI in Practice
We review practical challenges in building and deploying ethical AI at t...
research
∙
08/11/2021
Seven challenges for harmonizing explainability requirements
Regulators have signalled an interest in adopting explainable AI(XAI) te...
research
∙
07/15/2021
An Educational System for Personalized Teacher Recommendation in K-12 Online Classrooms
In this paper, we propose a simple yet effective solution to build pract...
research
∙
06/29/2021
Counterfactual Explanations for Arbitrary Regression Models
We present a new method for counterfactual explanations (CFEs) based on ...
research
∙
06/16/2021
Model-Based Counterfactual Synthesizer for Interpretation
Counterfactuals, serving as one of the emerging type of model interpreta...
research
∙
11/19/2020
Provable Multi-Objective Reinforcement Learning with Generative Models
Multi-objective reinforcement learning (MORL) is an extension of ordinar...
research
∙
11/04/2020
Debiasing classifiers: is reality at variance with expectation?
Many methods for debiasing classifiers have been proposed, but their eff...
research
∙
10/09/2020
CryptoCredit: Securely Training Fair Models
When developing models for regulated decision making, sensitive features...
research
∙
10/09/2020
Paying down metadata debt: learning the representation of concepts using topic models
We introduce a data management problem called metadata debt, to identify...
research
∙
10/09/2020
Towards Self-Regulating AI: Challenges and Opportunities of AI Model Governance in Financial Services
AI systems have found a wide range of application areas in financial ser...
research
∙
07/21/2020
3D Correspondence Grouping with Compatibility Features
We present a simple yet effective method for 3D correspondence grouping....
research
∙
05/16/2020
Neural Multi-Task Learning for Teacher Question Detection in Online Classrooms
Asking questions is one of the most crucial pedagogical techniques used ...
research
∙
04/09/2020
Heuristics for Link Prediction in Multiplex Networks
Link prediction, or the inference of future or missing connections betwe...
research
∙
04/07/2020
Model-Agnostic Characterization of Fairness Trade-offs
There exist several inherent trade-offs in designing a fair model, such ...
research
∙
09/01/2019
A Multimodal Alerting System for Online Class Quality Assurance
Online 1 on 1 class is created for more personalized learning experience...
research
∙
11/27/2018
Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved
Assessing the fairness of a decision making system with respect to a pro...
research
∙
09/12/2018
Fair lending needs explainable models for responsible recommendation
The financial services industry has unique explainability and fairness c...
research
∙
08/12/2018
Linguistic Relativity and Programming Languages
The use of programming languages can wax and wane across the decades. We...
research
∙
08/09/2018
Fast computation of the principal components of genotype matrices in Julia
Finding the largest few principal components of a matrix of genetic data...
research
∙
08/09/2018
Fast Flexible Function Dispatch in Julia
Technical computing is a challenging application area for programming la...
research
∙
08/15/2016