623 citations · 2.1k across the 30 of their papers we have counts for
33 papers
What "Form'' of Uncertainty Does Conformal Prediction Quantify?
Soroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Rebekka Burkholz +1
Conformal prediction (CP) is a post-hoc calibration method that returns prediction sets with distribution-free coverage guarantees, and the size of the output set is often interpre…
Reward-Gated On-Policy Distillation
Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi +3
On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the tea…
Test-Time Training Undermines Safety Guardrails
Simone Antonelli, Sadegh Akhondzadeh, Aleksandar Bojchevski
Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such as few-shot learning, retrieval…
EvA: Evolutionary Attacks on Graphs
Mohammad Sadegh Akhondzadeh, Soroush H. Zargarbashi, Jimin Cao +1
Even a slight perturbation in the graph structure can cause a significant drop in the accuracy of graph neural networks (GNNs). Most existing attacks leverage gradient information…
One Sample is Enough to Make Conformal Prediction Robust
Soroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski
For any black-box model, conformal prediction (CP) returns prediction sets guaranteed to include the true label with high adjustable probability. Robust CP (RCP) extends the guaran…
Optimal Conformal Prediction under Epistemic Uncertainty
Alireza Javanmardi, Soroush H. Zargarbashi, Santo M. A. R. Thies +3
Conformal prediction (CP) is a widely used frequentist framework to quantify uncertainty by constructing prediction sets with user-specified marginal coverage guarantees. In practi…
Robust Conformal Prediction with a Single Binary Certificate
Soroush H. Zargarbashi, Aleksandar Bojchevski
Conformal prediction (CP) converts any model's output to prediction sets with a guarantee to cover the true label with (adjustable) high probability. Robust CP extends this guarant…
KurTail : Kurtosis-based LLM Quantization
Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski, Evangelos Eleftheriou +1
One of the challenges of quantizing a large language model (LLM) is the presence of outliers. Outliers often make uniform quantization schemes less effective, particularly in extre…
SafePowerGraph: Safety-aware Evaluation of Graph Neural Networks for Transmission Power Grids
Salah Ghamizi, Aleksandar Bojchevski, Aoxiang Ma +1
Power grids are critical infrastructures of paramount importance to modern society and their rapid evolution and interconnections has heightened the complexity of power systems (PS…
Conformal Inductive Graph Neural Networks
Soroush H. Zargarbashi, Aleksandar Bojchevski
Conformal prediction (CP) transforms any model's output into prediction sets guaranteed to include (cover) the true label. CP requires exchangeability, a relaxation of the i.i.d. a…
Robust Yet Efficient Conformal Prediction Sets
Soroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski
Conformal prediction (CP) can convert any model's output into prediction sets guaranteed to include the true label with any user-specified probability. However, same as the model i…
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
Vijay Lingam, Atula Tejaswi, Aditya Vavre +7
Popular parameter-efficient fine-tuning (PEFT) methods, such as LoRA and its variants, freeze pre-trained model weights \(W\) and inject learnable matrices \(ΔW\). These \(ΔW\) mat…
Are GATs Out of Balance?
Nimrah Mustafa, Aleksandar Bojchevski, Rebekka Burkholz
While the expressive power and computational capabilities of graph neural networks (GNNs) have been theoretically studied, their optimization and learning dynamics, in general, rem…
Hierarchical Randomized Smoothing
Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski +1
Real-world data is complex and often consists of objects that can be decomposed into multiple entities (e.g. images into pixels, graphs into interconnected nodes). Randomized smoot…
Probing Graph Representations
Mohammad Sadegh Akhondzadeh, Vijay Lingam, Aleksandar Bojchevski
Today we have a good theoretical understanding of the representational power of Graph Neural Networks (GNNs). For example, their limitations have been characterized in relation to…
Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks
Jan Schuchardt, Aleksandar Bojchevski, Johannes Gasteiger +1
In tasks like node classification, image segmentation, and named-entity recognition we have a classifier that simultaneously outputs multiple predictions (a vector of labels) based…
Are Defenses for Graph Neural Networks Robust?
Felix Mujkanovic, Simon Geisler, Stephan Günnemann +1
A cursory reading of the literature suggests that we have made a lot of progress in designing effective adversarial defenses for Graph Neural Networks (GNNs). Yet, the standard met…
Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
Yan Scholten, Jan Schuchardt, Simon Geisler +2
Randomized smoothing is one of the most promising frameworks for certifying the adversarial robustness of machine learning models, including Graph Neural Networks (GNNs). Yet, exis…
Adversarial Weight Perturbation Improves Generalization in Graph Neural Networks
Yihan Wu, Aleksandar Bojchevski, Heng Huang
A lot of theoretical and empirical evidence shows that the flatter local minima tend to improve generalization. Adversarial Weight Perturbation (AWP) is an emerging technique to ef…
Unveiling the Sampling Density in Non-Uniform Geometric Graphs
Raffaele Paolino, Aleksandar Bojchevski, Stephan Günnemann +2
A powerful framework for studying graphs is to consider them as geometric graphs: nodes are randomly sampled from an underlying metric space, and any pair of nodes is connected if…
Localized Randomized Smoothing for Collective Robustness Certification
Jan Schuchardt, Tom Wollschläger, Aleksandar Bojchevski +1
Models for image segmentation, node classification and many other tasks map a single input to multiple labels. By perturbing this single shared input (e.g. the image) an adversary…
Robustness of Graph Neural Networks at Scale
Simon Geisler, Tobias Schmidt, Hakan Şirin +3
Graph Neural Networks (GNNs) are increasingly important given their popularity and the diversity of applications. Yet, existing studies of their vulnerability to adversarial attack…
Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
Simon Geisler, Johanna Sommer, Jan Schuchardt +2
End-to-end (geometric) deep learning has seen first successes in approximating the solution of combinatorial optimization problems. However, generating data in the realm of NP-hard…
Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More
Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann
Existing techniques for certifying the robustness of models for discrete data either work only for a small class of models or are general at the expense of efficiency or tightness.…