Author name cluster

Maximilian Thiessen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Marginal-Nonuniform PAC Learnability

Steve Hanneke
Shay Moran
Maximilian Thiessen

We revisit the classical model of nonuniform PAC learning, introduced by Benedek and Itai [1994], where generalization guarantees may depend on the target concept (but not on the marginal distribution). In this work, we study a complementary variant, which we call *marginal-nonuniform learning*. In this setting, guarantees may depend on the marginal distribution over the domain, but must hold uniformly over all concepts. This captures the intuition that some data distributions are inherently easier to learn from than others, allowing for a flexible, distribution-sensitive view of learnability. Our main result is a complete characterization of the achievable learning rates in this model, revealing a trichotomy: exponential rates of the form $e^{-n}$ arise precisely when the hypothesis class is finite; linear rates of the form $d/n$ are achievable when a recently introduced combinatorial parameter, the VC-eluder dimension $d$, is finite; and arbitrarily slow rates may occur when $d = \infty$. Additionally, in the original (concept-)nonuniform model, we show that for all learnable classes linear rates are achievable. We conclude by situating marginal-nonuniform learning within the landscape of universal learning, and by discussing its relationship to other distribution-dependent learning paradigms.

PDF Details

TMLR Journal 2025 Journal Article

Maximally Expressive GNNs for Outerplanar Graphs

Franka Bause
Fabian Jogl
Patrick Indri
Tamara Drucks
David Penz
Nils Morten Kriege
Thomas Gärtner
Pascal Welke

We propose a linear time graph transformation that enables the Weisfeiler-Leman (WL) algorithm and message passing graph neural networks (MPNNs) to be maximally expressive on outerplanar graphs. Our approach is motivated by the fact that most pharmaceutical molecules correspond to outerplanar graphs. Existing research predominantly enhances the expressivity of graph neural networks without specific graph families in mind. This often leads to methods that are impractical due to their computational complexity. In contrast, the restriction to outerplanar graphs enables us to encode the Hamiltonian cycle of each biconnected component in linear time. As the main contribution of the paper we prove that our method achieves maximum expressivity on outerplanar graphs. Experiments confirm that our graph transformation improves the predictive performance of MPNNs on molecular benchmark datasets at negligible computational overhead.

PDF Details

NeurIPS Conference 2024 Conference Paper

Bandits with Abstention under Expert Advice

Stephen Pasteris
Alberto Rumi
Maximilian Thiessen
Shota Saito
Atsushi Miyauchi
Fabio Vitale
Mark Herbster

We study the classic problem of prediction with expert advice under bandit feedback. Our model assumes that one action, corresponding to the learner's abstention from play, has no reward or loss on every trial. We propose the CBA (Confidence-rated Bandits with Abstentions) algorithm, which exploits this assumption to obtain reward bounds that can significantly improve those of the classical Exp4 algorithm. Our problem can be construed as the aggregation of confidence-rated predictors, with the learner having the option to abstain from play. We are the first to achieve bounds on the expected cumulative reward for general confidence-rated predictors. In the special case of specialists, we achieve a novel reward bound, significantly improving previous bounds of SpecialistExp (treating abstention as another action). We discuss how CBA can be applied to the problem of adversarial contextual bandits with the option of abstaining from selecting any action. We are able to leverage a wide range of inductive biases, outperforming previous approaches both theoretically and in preliminary experimental analysis. Additionally, we achieve a reduction in runtime from quadratic to almost linear in the number of contexts for the specific case of metric space contexts.

PDF Details DOI

ICML Conference 2023 Conference Paper

Expectation-Complete Graph Representations with Homomorphisms

Pascal Welke
Maximilian Thiessen
Fabian Jogl
Thomas Gärtner 0001

We investigate novel random graph embeddings that can be computed in expected polynomial time and that are able to distinguish all non-isomorphic graphs in expectation. Previous graph embeddings have limited expressiveness and either cannot distinguish all graphs or cannot be computed efficiently for every graph. To be able to approximate arbitrary functions on graphs, we are interested in efficient alternatives that become arbitrarily expressive with increasing resources. Our approach is based on Lovász’ characterisation of graph isomorphism through an infinite dimensional vector of homomorphism counts. Our empirical evaluation shows competitive results on several benchmark graph learning tasks.

Details

NeurIPS Conference 2023 Conference Paper

Expressivity-Preserving GNN Simulation

Fabian Jogl
Maximilian Thiessen
Thomas Gärtner

We systematically investigate graph transformations that enable standard message passing to simulate state-of-the-art graph neural networks (GNNs) without loss of expressivity. Using these, many state-of-the-art GNNs can be implemented with message passing operations from standard libraries, eliminating many sources of implementation issues and allowing for better code optimization. We distinguish between weak and strong simulation: weak simulation achieves the same expressivity only after several message passing steps while strong simulation achieves this after every message passing step. Our contribution leads to a direct way to translate common operations of non-standard GNNs to graph transformations that allow for strong or weak simulation. Our empirical evaluation shows competitive predictive performance of message passing on transformed graphs for various molecular benchmark datasets, in several cases surpassing the original GNNs.

PDF Details

NeurIPS Conference 2022 Conference Paper

Active Learning of Classifiers with Label and Seed Queries

Marco Bressan
Nicolò Cesa-Bianchi
Silvio Lattanzi
Andrea Paudice
Maximilian Thiessen

We study exact active learning of binary and multiclass classifiers with margin. Given an $n$-point set $X \subset \mathbb{R}^m$, we want to learn an unknown classifier on $X$ whose classes have finite strong convex hull margin, a new notion extending the SVM margin. In the standard active learning setting, where only label queries are allowed, learning a classifier with strong convex hull margin $\gamma$ requires in the worst case $\Omega\big(1+\frac{1}{\gamma}\big)^{\frac{m-1}{2}}$ queries. On the other hand, using the more powerful \emph{seed} queries (a variant of equivalence queries), the target classifier could be learned in $O(m \log n)$ queries via Littlestone's Halving algorithm; however, Halving is computationally inefficient. In this work we show that, by carefully combining the two types of queries, a binary classifier can be learned in time $\operatorname{poly}(n+m)$ using only $O(m^2 \log n)$ label queries and $O\big(m \log \frac{m}{\gamma}\big)$ seed queries; the result extends to $k$-class classifiers at the price of a $k! k^2$ multiplicative overhead. Similar results hold when the input points have bounded bit complexity, or when only one class has strong convex hull margin against the rest. We complement the upper bounds by showing that in the worst case any algorithm needs $\Omega\big(k m \log \frac{1}{\gamma}\big)$ seed and label queries to learn a $k$-class classifier with strong convex hull margin $\gamma$.

PDF Details

NeurIPS Conference 2021 Conference Paper

Active Learning of Convex Halfspaces on Graphs

Maximilian Thiessen
Thomas Gaertner

We systematically study the query complexity of learning geodesically convex halfspaces on graphs. Geodesic convexity is a natural generalisation of Euclidean convexity and allows the definition of convex sets and halfspaces on graphs. We prove an upper bound on the query complexity linear in the treewidth and the minimum hull set size but only logarithmic in the diameter. We show tight lower bounds along well-established separation axioms and identify the Radon number as a central parameter of the query complexity and the VC dimension. While previous bounds typically depend on the cut size of the labelling, all parameters in our bounds can be computed from the unlabelled graph. We provide evidence that ground-truth communities in real-world graphs are often convex and empirically compare our proposed approach with other active learning algorithms.

PDF Details