Author name cluster

Michael Cochez

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.

11 papers

2 author rows

TMLR Journal 2026 Journal Article

Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxation

Yannick Brunink
Daniel Daza
Yunjie He
Michael Cochez

Neural methods for Complex Query Answering (CQA) over knowledge graphs (KGs) are widely believed to learn patterns that generalize beyond explicit graph structure, allowing them to infer answers that are unreachable through symbolic query processing. In this work, we critically examine this assumption through a systematic analysis comparing neural CQA models with an alternative, training-free query relaxation strategy that retrieves possible answers by relaxing query constraints and counting resulting paths. Across multiple datasets and query structures, we find several cases where neural and relaxation-based approaches perform similarly, with no neural model consistently outperforming the latter. Moreover, a similarity analysis reveals that their retrieved answers exhibit little overlap, and that combining their outputs consistently improves performance. These results call for a re-evaluation of progress in neural query answering: despite their complexity, current models fail to subsume the reasoning patterns captured by query relaxation. Our findings highlight the importance of stronger non-neural baselines and suggest that future neural approaches could benefit from incorporating principles of query relaxation.

PDF Details

TMLR Journal 2026 Journal Article

Explaining Graph Neural Networks for Node Similarity on Graphs

Daniel Daza
Cuong Xuan Chu
Trung-Kien Tran
Daria Stepanova
Michael Cochez
Paul Groth

Similarity search is a fundamental task for exploiting information in various applications dealing with graph data, such as citation networks or knowledge graphs. Prior work on the explainability of graph neural networks (GNNs) has focused on supervised tasks, such as node classification and link prediction. However, the challenge of explaining similarities between node embeddings has been left unaddressed. We take a step towards filling this gap by formulating the problem, identifying desirable properties of explanations of similarity, and proposing intervention-based metrics that qualitatively assess them. Using our framework, we evaluate the performance of representative methods for explaining GNNs, based on the concepts of mutual information (MI) and gradient-based (GB) explanations. We find that unlike MI explanations, GB explanations have three desirable properties. First, they are actionable: selecting particular inputs results in predictable changes in similarity scores of corresponding nodes. Second, they are consistent: the effect of selecting certain inputs hardly overlaps with the effect of discarding them. Third, they can be pruned significantly to obtain sparse explanations that retain the effect on similarity scores. These important findings highlight the utility of our metrics as a framework for evaluating the quality of explanations of node similarities in GNNs.

PDF Details

NeSy Conference 2025 Conference Paper

Do Graph Neural Network States Contain Graph Properties?

Tom Pelletreau-Duris
Ruud van Bakel
Michael Cochez

Deep neural networks (DNNs) achieve state-of-the-art performance on many tasks, but this often requires increasingly larger model sizes, which in turn leads to more complex internal representations. Explainability techniques (XAI) have made remarkable progress in the interpretability of ML models. However, the non-euclidean nature of Graph Neural Networks (GNNs) makes it difficult to reuse already existing XAI methods. While other works have focused on instance-based explanation methods for GNNs, very few have investigated model-based methods and, to our knowledge, none have tried to probe the embedding of the GNNs for structural graph properties. In this paper we present a model agnostic explainability pipeline for Graph Neural Networks (GNNs) employing diagnostic classifiers. We propose to consider graph-theoretic properties as the features of choice for studying the emergence of representations in GNNs. This pipeline aims to probe and interpret the learned representations in GNNs across various architectures and datasets, refining our understanding and trust in these models.

Details

NeSy Conference 2025 Conference Paper

The ART of Link Prediction with KGEs

Yannick Brunink
Michael Cochez
Jacopo Urbani

Link Prediction (LP) in Knowledge Graphs (KGs) is typically framed as ranking candidate entities for a query of the form $(entity, relation, ?)$, with models evaluated on their ability to rank the correct entities for each query. At the same time, Knowledge Graph Embedding (KGE) models used for this task produce unnormalised scores, making it unclear how to interpret their belief in the truthfulness of triples across different queries. Together, these two factors create a blind spot: models can achieve perfect rankings while assigning scores that are not comparable across queries, limiting their utility in downstream tasks or even in identifying the most plausible triples overall. Indeed, this issue becomes clear when test triples are ranked globally and evaluated with IR metrics, revealing that models with unnormalized scores often perform poorly due to inconsistent scoring across queries. To address this problem, we propose a new KGE model, called ART, which exploits probabilistic Auto-Regressive modelling and hence is normalised by design. Despite its conceptual simplicity, we show that ART outperforms prior art for discriminative and generative LP as well as other post-hoc calibration techniques.

Details

TMLR Journal 2024 Journal Article

Neural Graph Reasoning: A Survey on Complex Logical Query Answering

Hongyu Ren
Mikhail Galkin
Zhaocheng Zhu
Jure Leskovec
Michael Cochez

Complex logical query answering (CLQA) is a recently emerged task of graph machine learning that goes beyond simple one-hop link prediction and solves the far more complex task of multi-hop logical reasoning over massive, potentially incomplete graphs. The task received significant traction in the community; numerous works expanded the field along theoretical and practical axes to tackle different types of complex queries and graph modalities with efficient systems. In this paper, we provide a holistic survey of CLQA with a detailed taxonomy studying the field from multiple angles, including graph types (modality, reasoning domain, background semantics), modeling aspects (encoder, processor, decoder), supported queries (operators, patterns, projected variables), datasets, evaluation metrics, and applications. Finally, we point out promising directions, unsolved problems and applications of CLQA for future research.

PDF Details

AAAI Conference 2023 Conference Paper

A Machine with Short-Term, Episodic, and Semantic Memory Systems

Taewoon Kim
Michael Cochez
Vincent Francois-Lavet
Mark Neerincx
Piek Vossen

Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph. To evaluate this system and analyze the behavior of this agent, we designed and released our own reinforcement learning agent environment, “the Room”, where an agent has to learn how to encode, store, and retrieve memories to maximize its return by answering questions. We show that our deep Q-learning based agent successfully learns whether a short-term memory should be forgotten, or rather be stored in the episodic or semantic memory systems. Our experiments indicate that an agent with human-like memory systems can outperform an agent without this memory structure in the environment.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Adapting Neural Link Predictors for Data-Efficient Complex Query Answering

Erik Arakelyan
Pasquale Minervini
Daniel Daza
Michael Cochez
Isabelle Augenstein

Answering complex queries on incomplete knowledge graphs is a challenging task where a model needs to answer complex logical queries in the presence of missing knowledge. Prior work in the literature has proposed to address this problem by designing architectures trained end-to-end for the complex query answering task with a reasoning process that is hard to interpret while requiring data and resource-intensive training. Other lines of research have proposed re-using simple neural link predictors to answer complex queries, reducing the amount of training data by orders of magnitude while providing interpretable answers. The neural link predictor used in such approaches is not explicitly optimised for the complex query answering task, implying that its scores are not calibrated to interact together. We propose to address these problems via CQD$^{\mathcal{A}}$, a parameter-efficient score \emph{adaptation} model optimised to re-calibrate neural link prediction scores for the complex query answering task. While the neural link predictor is frozen, the adaptation component -- which only increases the number of model parameters by $0. 03\%$ -- is trained on the downstream complex query answering task. Furthermore, the calibration component enables us to support reasoning over queries that include atomic negations, which was previously impossible with link predictors. In our experiments, CQD$^{\mathcal{A}}$ produces significantly more accurate results than current state-of-the-art methods, improving from $34. 4$ to $35. 1$ Mean Reciprocal Rank values averaged across all datasets and query types while using $\leq 30\%$ of the available training query types. We further show that CQD$^{\mathcal{A}}$ is data-efficient, achieving competitive results with only $1\%$ of the complex training queries and robust in out-of-domain evaluations. Source code and datasets are available at https: //github. com/EdinburghNLP/adaptive-cqd.

PDF Details

IJCAI Conference 2022 Conference Paper

Complex Query Answering with Neural Link Predictors (Extended Abstract)*

Pasquale Minervini
Erik Arakelyan
Daniel Daza
Michael Cochez

Neural link predictors are useful for identifying missing edges in large scale Knowledge Graphs. However, it is still not clear how to use these models for answering more complex queries containing logical conjunctions (∧), disjunctions (∨), and existential quantifiers (∃). We propose a framework for efficiently answering complex queries on in- complete Knowledge Graphs. We translate each query into an end-to-end differentiable objective, where the truth value of each atom is computed by a pre-trained neural link predictor. We then analyse two solutions to the optimisation problem, including gradient-based and combinatorial search. In our experiments, the proposed approach produces more accurate results than state-of-the-art methods — black-box models trained on millions of generated queries — without the need for training on a large and diverse set of complex queries. Using orders of magnitude less training data, we obtain relative improvements ranging from 8% up to 40% in Hits@3 across multiple knowledge graphs. We find that it is possible to explain the outcome of our model in terms of the intermediate solutions identified for each of the complex query atoms. All our source code and datasets are available online (https: //github. com/uclnlp/cqd).

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Hyperbolic Embedding Inference for Structured Multi-Label Prediction

Bo Xiong
Michael Cochez
Mojtaba Nayyeri
Steffen Staab

We consider a structured multi-label prediction problem where the labels are organized under implication and mutual exclusion constraints. A major concern is to produce predictions that are logically consistent with these constraints. To do so, we formulate this problem as an embedding inference problem where the constraints are imposed onto the embeddings of labels by geometric construction. Particularly, we consider a hyperbolic Poincaré ball model in which we encode labels as Poincaré hyperplanes that work as linear decision boundaries. The hyperplanes are interpreted as convex regions such that the logical relationships (implication and exclusion) are geometrically encoded using the insideness and disjointedness of these regions, respectively. We show theoretical groundings of the method for preserving logical relationships in the embedding space. Extensive experiments on 12 datasets show 1) significant improvements in mean average precision; 2) lower number of constraint violations; 3) an order of magnitude fewer dimensions than baselines.

PDF Details

ICLR Conference 2022 Conference Paper

Query Embedding on Hyper-Relational Knowledge Graphs

Dimitrios Alivanistos
Max Berrendorf
Michael Cochez
Mikhail Galkin 0001

Multi-hop logical reasoning is an established problem in the field of representation learning on knowledge graphs (KGs). It subsumes both one-hop link prediction as well as other more complex types of logical queries. Existing algorithms operate only on classical, triple-based graphs, whereas modern KGs often employ a hyper-relational modeling paradigm. In this paradigm, typed edges may have several key-value pairs known as qualifiers that provide fine-grained context for facts. In queries, this context modifies the meaning of relations, and usually reduces the answer set. Hyper-relational queries are often observed in real-world KG applications, and existing approaches for approximate query answering cannot make use of qualifier pairs. In this work, we bridge this gap and extend the multi-hop reasoning problem to hyper-relational KGs allowing to tackle this new type of complex queries. Building upon recent advancements in Graph Neural Networks and query embedding techniques, we study how to embed and answer hyper-relational conjunctive queries. Besides that, we propose a method to answer such queries and demonstrate in our experiments that qualifiers improve query answering on a diverse set of query patterns.

Details

ICLR Conference 2021 Conference Paper

Complex Query Answering with Neural Link Predictors

Erik Arakelyan
Daniel Daza
Pasquale Minervini
Michael Cochez

Neural link predictors are immensely useful for identifying missing edges in large scale Knowledge Graphs. However, it is still not clear how to use these models for answering more complex queries that arise in a number of domains, such as queries using logical conjunctions ($\land$), disjunctions ($\lor$) and existential quantifiers ($\exists$), while accounting for missing edges. In this work, we propose a framework for efficiently answering complex queries on incomplete Knowledge Graphs. We translate each query into an end-to-end differentiable objective, where the truth value of each atom is computed by a pre-trained neural link predictor. We then analyse two solutions to the optimisation problem, including gradient-based and combinatorial search. In our experiments, the proposed approach produces more accurate results than state-of-the-art methods --- black-box neural models trained on millions of generated queries --- without the need of training on a large and diverse set of complex queries. Using orders of magnitude less training data, we obtain relative improvements ranging from 8% up to 40% in Hits@3 across different knowledge graphs containing factual information. Finally, we demonstrate that it is possible to explain the outcome of our model in terms of the intermediate solutions identified for each of the complex query atoms. All our source code and datasets are available online, at https://github.com/uclnlp/cqd.

Details