36 citations · 51 across the 14 of their papers we have counts for
15 papers
Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors
Oliver Makins, Orazio Angelini, Zohreh Shams +1
AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent. AI Control usually studies a single agent in one trajectory, but r…
Explaining Surface Layer Theory Departures in Marine Flux Profiles with Data-Driven Discovery
Jack Foxabbott, Leo Mckee-Reid, Andrew Cusick +8
Monin--Obukhov Similarity Theory (MOST), which underpins nearly all bulk estimates of surface fluxes in the atmospheric surface layer, assumes monotonic wind profiles and verticall…
Benchmarking the Discovery Engine
Jack Foxabbott, Arush Tagade, Andrew Cusick +6
The Discovery Engine is a general purpose automated system for scientific discovery, which combines machine learning with state-of-the-art ML interpretability to enable rapid and r…
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
Mateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero +2
In this paper, we investigate how concept-based models (CMs) respond to out-of-distribution (OOD) inputs. CMs are interpretable neural architectures that first predict a set of hig…
Efficient Bias Mitigation Without Privileged Information
Mateo Espinosa Zarlenga, Swami Sankaranarayanan, Jerone T. A. Andrews +3
Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously…
Gene Expression Patterns of CsZCD and Apocarotenoid Accumulation during Saffron Stigma Development
Zohreh Shams
Crocus sativus L., otherwise known as saffron, is a highly prized plant due to its unique triploid capability and elongated stigmas, contributing to its status as the costly spice…
Learning to Receive Help: Intervention-Aware Concept Embedding Models
Mateo Espinosa Zarlenga, Katherine M. Collins, Krishnamurthy Dvijotham +3
Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property…
CGXplain: Rule-Based Deep Neural Network Explanations Using Dual Linear Programs
Konstantin Hemker, Zohreh Shams, Mateja Jamnik
Rule-based surrogate models are an effective and interpretable way to approximate a Deep Neural Network's (DNN) decision boundaries, allowing humans to easily understand deep learn…
Towards Robust Metrics for Concept Representation Evaluation
Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams +4
Recent work on interpretability has focused on concept-based explanations, where deep learning models are explained in terms of high-level units of information, referred to as conc…
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna +9
Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworth…
Efficient Decompositional Rule Extraction for Deep Neural Networks
Mateo Espinosa Zarlenga, Zohreh Shams, Mateja Jamnik
In recent years, there has been significant work on increasing both interpretability and debuggability of a Deep Neural Network (DNN) by extracting a rule-based model that approxim…
Using ontology embeddings for structural inductive bias in gene expression data analysis
Maja Trębacz, Zohreh Shams, Mateja Jamnik +4
Stratifying cancer patients based on their gene expression levels allows improving diagnosis, survival analysis and treatment planning. However, such data is extremely highly dimen…
Incorporating network based protein complex discovery into automated model construction
Paul Scherer, Maja Trȩbacz, Nikola Simidjievski +4
We propose a method for gene expression based analysis of cancer phenotypes incorporating network biology knowledge through unsupervised construction of computational graphs. The s…
MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library
Dmitry Kazhdan, Zohreh Shams, Pietro Liò
Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields. An effective way to further empower these…
Practical Reasoning with Norms for Autonomous Software Agents (Full Edition)
Zohreh Shams, Marina De Vos, Julian Padget +1
Autonomous software agents operating in dynamic environments need to constantly reason about actions in pursuit of their goals, while taking into consideration norms which might be…