Deng Pan
9 papers · 2020–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI
(4)
Core Methods
(4)
Optimization & Theory · Machine Learning
(4)
Learning Types · Deep Learning
(3)
Optimization & Theory · Deep Learning
(3)
Data Science & Analytics
(1)
Natural Language Processing
(1)
Speech & Audio
(1)
Application Areas
(1)
Applications
(1)
Architectures
(1)
Learning Types · Machine Learning
(1)
Keywords
gradient attribution
(2)
feature importance
(2)
neural network
(2)
feature attribution
(2)
convolutional neural network
(2)
feature distribution
(1)
collaborative filtering
(1)
stochastic gradient descent
(1)
neural network interpretability
(1)
deep neural network
(1)
policy gradient
(1)
class imbalance
(1)
model interpretability
(1)
multi-class classification
(1)
latent factor model
(1)
automatic speech recognition
(1)
feature mapping
(1)
logistic loss
(1)
attention mechanism
(1)
adversarial robustness
(1)
Papers
Fast Explanations via Policy Gradient-Optimized Explainer
IJCAI 2025
Leveraging Artificial Intelligence to Bridge Gaps in Pediatric Oncology Care for Marginalized Spanish-Speaking Communities
IJCAI 2025
Learning Compact Features via In-Training Representation Alignment
AAAI 2023
Negative Flux Aggregation to Estimate Feature Attributions
IJCAI 2023
AttCAT: Explaining Transformers via Attentive Class Activation Tokens
NeurIPS 2022
Explaining Deep Neural Network Models with Adversarial Gradient Integration
IJCAI 2021
Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints
AAAI 2021
Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability
IJCAI 2020
On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks
AAAI 2020