-
The Scientometrics of AI Benchmarks: Unveiling the Underlying Mechanics of AI Research
Conference Paper by P Barredo, José Hernández-Orallo, F Martinez-Plumed, Seán Ó hÉigeartaigh
-
Co-designing Resources for Ethics Education in HCI
Conference Paper by G Pillai et al incl., Rafael Calvo
-
Pitfalls of Learning a Reward Function Online
Conference Paper by Stuart Armstrong, J Leike, L Orseau, S Legg
-
Now You See Me (CME): Concept-based Model Extraction
Conference Paper by D Kazhdan, B Dimanov, Mateja Jamnik, P Lio, Adrian Weller
-
Getting a CLUE: A method for explaining uncertainty estimates
Conference Paper by J Antoran et al, Umang Bhatt, Adrian Weller
-
On the Fairness of Causal Algorithmic Recourse
Conference Paper by J von Kügelgen et al incl., Umang Bhatt, Adrian Weller
-
Machine Learning Explainability for External Stakeholders
Conference Paper by Umang Bhatt, M Andrus, Adrian Weller, A Xiang
-
Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch
Conference Paper by L Viano et al incl., Adrian Weller
-
Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices
Conference Paper by V Likhoshertov, J Davis, K Choromanski, Adrian Weller
-
An Algorithmic Framework for Positive Action
Conference Paper by O Thomas, Miri Zilka, Adrian Weller, N Quadrianto
-
Improving Interpretability in Medical Imaging Diagnosis using Adversarial Training
Conference Paper by A Margeliou, N Simidjevski, Mateja Jamnik, Adrian Weller
-
PyCID: A Python Library for Causal Influence Diagrams
Conference Paper by J Fox, T Everitt, Ryan Carey, E Langlois, A Abate, M Woolridge
-
Iterative Teaching by Label Synthesis
Conference Paper by Weiyang Liu, Z Liu, H Wang, L Paull, B Scholkopf, Adrian Weller
-
Agent Incentives: A Causal Perspective
Conference Paper by T Everitt, Ryan Carey, E Langlois, P A Ortega, S Legg
-
Beyond Reasonable Doubt: Improving Fairness in Budget-Constrained Decision Making Using Confidence Thresholds
Conference Paper by M Bakker et al, Adrian Weller
-
Sub-Linear Memory: How to Make Performers SLiM
Conference Paper by V Likhoshertov, K Chromoanski, J Davis, X Song, Adrian Weller
-
Effects of Uncertainty on the Quality of Feature Importance Estimates
Conference Paper by T Shaikhina, Umang Bhatt, R Zhang, K Georgatzis, A Xiang, Adrian Weller
-
Learning with Hyperspherical Uniformity
Conference Paper by Weiyang Liu, R Lin, Z Liu, L Xiong, B Scholkopf, Adrian Weller
-
Rethinking Attention with Performers
Conference Paper by K Choromanski et al incl., Adrian Weller
-
Orthogonal Over-Parameterized Training
Conference Paper by Weiyang Liu, R Lin, Z Liu et al incl., Adrian Weller
-
Stochastic Flows and Geometric Optimization on the Orthogonal Group
Conference Paper by K Choromanski et al incl., Adrian Weller
-
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Conference Paper by Adrian Weller, Umang Bhatt
-
Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Conference Paper by V Likhoshertov, X Song, K Choromanski, J Davis, Adrian Weller
-
Machine Learning and the Meaning of Equal Treatment
Conference Paper by J Simons, S Adams Bhatti, Adrian Weller
-
Rethinking Attention with Performers
Conference Paper by Krzysztof Choromanski, Valerii Likhosherstov, David Dohan, Xingyou Song, Andreea Gane, Tamas Sarlos, Peter Hawkins, Jared Davis, Afroz Mohiuddin, Lukasz Kaiser, David Belanger, Lucy Colwell, Adrian Weller
-
An Algorithmic Framework for Positive Action
Conference Paper by Oliver Thomas, Miri Zilka, Adrian Weller, Novi Quadrianto
-
PyCID: A Python Library for Causal Influence Diagrams
Conference Paper by James Fox, Tom Everitt, Ryan Carey, Eric Langlois, Alessandro Abate, Michael Wooldridge
-
Iterative Teaching by Label Synthesis. In Neural Information Processing Systems
Conference Paper by Weiyang Liu, Zhen Liu, Hanchen Wang, Liam Paull, Bernhard Schölkopf, Adrian Weller
-
Co-designing Resources for Ethics Education in HCI
Conference Paper by Ajit G Pillai, A Baki Kocaballi, Tuck Wah Leong, Rafael Calvo, Nassim Parvin, Katie Shilton, Jenny Waycott, Casey Fiesler, John C. Havens, Naseem Ahmadpour
-
Stochastic Flows and Geometric Optimization on the Orthogonal Group
Conference Paper by Krzysztof Choromanski, David Cheikhi , Jared Davis , Valerii Likhosherstov , Adrian Weller
-
AI Paradigms and AI Safety: Mapping Artefacts and Techniques to Safety Issues
Conference Paper by José Hernández-Orallo, Fernando Martınez-Plumed, Shahar Avin, Jess Whittlestone, Seán Ó hÉigeartaigh
-
Evaluating and Aggregating Feature-based Model Explanations
Conference Paper by Umang Bhatt, Adrian Weller, Jose M. F. Moura
-
Adversarial Graph Embeddings for Fair Influence Maximization over Social Networks
Conference Paper by Moein Khajehnejad, Ahmad Asgharian Rezaei, Mahmoudreza Babaei, Jessica Hoffmann, Mahdi Jalili, Adrian Weller
-
You shouldn't trust me: Learning models which conceal unfairness from multiple explanation methods
Conference Paper by Botty Dimanov, Umang Bhatt, Mateja Jamnik, Adrian Weller
-
Beyond Near- and Long-Term: Towards a Clearer Account of Research Priorities in AI Ethics and Society
Conference Paper by Carina Prunkl, Jess Whittlestone
-
The Problem with Intelligence: Its Value-Laden History and the Future of AI
Conference Paper by Stephen Cave
-
An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision
Conference Paper by Hanchen Wang, Nina Grgić-Hlača, Preethi Lahoti, Krishna P. Gummadi, Adrian Weller
-
Explainable Machine Learning in Deployment
Conference Paper by Umang Bhatt, Alice Xiang, Shubham Sharma, Adrian Weller, Ankur Taly, Yunhan Jia, Joydeep Ghosh, Ruchir Puri, José M. F. Moura, Peter Eckersley
-
Defining and Unpacking Transformative AI
Conference Paper by Ross Gruetzemacher, Jess Whittlestone
-
The tension between openness and prudence in responsible AI research
Conference Paper by Jess Whittlestone, Aviv Ovadya
-
The Sensitivity of Counterfactual Fairness to Unmeasured Confounding
Conference Paper by Niki Kilbertus, Philip J. Ball, Matt J. Kusner, Adrian Weller, Ricardo Silva
-
TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning
Conference Paper by Tameem Adel Hesham, Adrian Weller
-
Surveying Safety-relevant AI Characteristics
Conference Paper by José Hernández-Orallo, Fernando Martınez-Plumed, Shahar Avin, Seán Ó hÉigeartaigh
-
Challenges for Transparency
Conference Paper by Adrian Weller
-
The Role and Limits of Principles in AI Ethics: Towards a Focus on Tensions
Conference Paper by Jess Whittlestone, Rune Nyrup, Anna Alexandrova, Stephen Cave
-
AI Extenders: The Ethical and Societal Implications of Humans Cognitively Extended by AI
Conference Paper by José Hernández-Orallo, Karina Vold
-
Why Artificial Consciousness Matters
Conference Paper by Matthew McGill
-
To build conscious machines, focus on general intelligence: a framework for the assessment of consciousness in biological and artificial systems
Conference Paper by Henry Shevlin
-
One-network Adversarial Fairness
Conference Paper by Tameem Adel Hesham, Isabel Valera, Zoubin Ghahramani, Adrian Weller
-
“Scary Robots”: Examining Public Responses to AI
Conference Paper by Stephen Cave, Kate Coughlan, Kanta Dihal
-
Blind Justice: Fairness with Encrypted Sensitive Attributes
Conference Paper by Niki Kilbertus, Adria Gascon, Matt Kusner, Michael Veale, Krishna P. Gummadi, Adrian Weller
-
The Off-Switch Game
Conference Paper by Dylan Hadfield-Menell, Anca Dragan, Pieter Abbeel, Stuart Russell
-
The Facets of Artificial Intelligence: A Framework to Track the Evolution of AI
Conference Paper by Fernando Martınez-Plumed, Bao Sheng Loe, Peter Flach, Seán Ó hÉigeartaigh, Karina Vold, José Hernández-Orallo
-
Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction
Conference Paper by Nina Grgić-Hlača, Elissa M. Redmiles, Krishna P. Gummadi, Adrian Weller
-
Purple Feed: Identifying High Consensus News Posts on Social Media
Conference Paper by Mahmoudreza Babaei, Juhi Kulshrestha, Abhijnan Chakraborty, Fabrıcio Benevenuto, Krishna P. Gummadi, Adrian Weller
-
Beyond Distributive Fairness in Algorithmic Decision Making: Feature Selection for Procedurally Fair Learning
Conference Paper by Nina Grgić-Hlača, Muhammad Bilal Zafar, Krishna P. Gummadi, Adrian Weller
-
Discovering interpretable representations for both deep generative and discriminative models
Conference Paper by Tameem Adel Hesham, Zoubin Ghahramani, Adrian Weller
-
From Parity to Preference-based Notions of Fairness in Classification
Conference Paper by Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, Krishna P. Gummadi, Adrian Weller
-
Mapping Intelligence: Requirements and Possibilities
Conference Paper by Anna Alexandrova, Shahar Avin, Stephen Cave, Lucy Cheke, Matthew McGill, Jan Feyereisl, Marta Halina, Bao Sheng Loe, Seán Ó hÉigeartaigh, Fernando Martinez-Plumed, Huw Price, Henry Shevlin, Adrian Weller, Alan Winfield, José Hernández-Orallo