Author name cluster

Gillian Dobbie

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.

9 papers

2 author rows

AAAI Conference 2026 Conference Paper

Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMs

Liu Yu
Zhonghao Chen
Ping Kuang
Zhikun Feng
Fan Zhou
Lan Wang
Gillian Dobbie

Object hallucination remains a critical challenge in Large Vision-Language Models (LVLMs), where models generate content inconsistent with visual inputs. Existing language-decoder based mitigation approaches often regulate visual or textual attention independently, overlooking their interaction as two key causal factors. To address this, we propose Owl (Bi-mOdal attention reWeighting for Layer-wise hallucination mitigation), a causally-grounded framework that models hallucination process via a structural causal graph, treating decomposed visual and textual attentions as mediators. We introduce VTACR (Visual-to-Textual Attention Contribution Ratio), a novel metric that quantifies the modality contribution imbalance during decoding. Our analysis reveals that hallucinations frequently occur in low-VTACR scenarios, where textual priors dominate and visual grounding is weakened. To mitigate this, we design a fine-grained attention intervention mechanism that dynamically adjusts token- and layer-wise attention guided by VTACR signals. Finally, we propose a dual-path contrastive decoding strategy: one path emphasizes visually grounded predictions, while the other amplifies hallucinated ones -- letting visual truth shine and hallucination collapse. Experimental results on the POPE and CHAIR benchmarks show that Owl achieves significant hallucination reduction, setting a new SOTA in faithfulness while preserving vision-language understanding capability. Our code is available at https://github.com/CikZ2023/OWL

PDF Details DOI

TMLR Journal 2026 Journal Article

Socrates Loss: Unifying Confidence Calibration and Classification by Leveraging the Unknown

Sandra Gómez-Gálvez
Tobias Olenyi
Gillian Dobbie
Katerina Taskova

Deep neural networks, despite their high accuracy, often exhibit poor confidence calibration, limiting their reliability in high-stakes applications. Current ad-hoc confidence calibration methods attempt to fix this during training but face a fundamental trade-off: two-phase training methods achieve strong classification performance at the cost of training instability and poorer confidence calibration, while single-loss methods are stable but underperform in classification. This paper addresses and mitigates this stability-performance trade-off. We propose Socrates Loss, a novel, unified loss function that explicitly leverages uncertainty by incorporating an auxiliary unknown class, whose predictions directly influence the loss function and a dynamic uncertainty penalty. This unified objective allows the model to be optimized for both classification and confidence calibration simultaneously, without the instability of complex, scheduled losses. We provide theoretical guarantees that our method regularizes the model to prevent miscalibration and overfitting. Across four benchmark datasets and multiple architectures, our comprehensive experiments demonstrate that Socrates Loss consistently improves training stability while achieving more favorable accuracy-calibration trade-off, often converging faster than existing methods.

PDF Details

IJCAI Conference 2025 Conference Paper

Balancing Invariant and Specific Knowledge for Domain Generalization with Online Knowledge Distillation

Di Zhao
Jingfeng Zhang
Hongsheng Hu
Philippe Fournier-Viger
Gillian Dobbie
Yun Sing Koh

Recent research has demonstrated the effectiveness of knowledge distillation in Domain Generalization. However, existing approaches often overlook domain-specific knowledge and rely on an offline distillation strategy, limiting the effectiveness of knowledge transfer. To address these limitations, we propose Balanced Online knowLedge Distillation (BOLD). BOLD leverages a multi-domain expert teacher model, with each expert specializing in a specific source domain, enabling the student to distill both domain-invariant and domain-specific knowledge. We incorporate the Pareto optimization principle and uncertainty weighting to balance these two types of knowledge, ensuring simultaneous optimization without compromising either. Additionally, BOLD employs an online knowledge distillation strategy, allowing the teacher and student to learn concurrently. This dynamic interaction enables the teacher to adapt based on student feedback, facilitating more effective knowledge transfer. Extensive experiments on seven benchmarks demonstrate that BOLD outperforms state-of-the-art methods. Furthermore, we provide theoretical insights that highlight the importance of domain-specific knowledge and the advantages of uncertainty weighting.

PDF Details DOI

AAMAS Conference 2024 Conference Paper

Behaviour Modelling of Social Animals via Causal Structure Discovery and Graph Neural Networks

Gaël Gendron
Yang Chen
Mitchell Rogers
Yiping Liu
Mihailo Azhar
Shahrokh Heidari
David Arturo Soriano Valdez
Kobe Knowles

Better understanding the natural world is a crucial task with a wide range of applications. In environments with close proximity between humans and animals, such as zoos, it is essential to better understand the causes behind animal behaviour to predict unusual changes, mitigate their detrimental effects and increase the well-being of animals. However, the complex social behaviours of mammalian groups remain largely unexplored. In this work, we propose a method to build behavioural models using causal structure discovery and graph neural networks for time series. We apply this method to a mob of meerkats in a zoo environment and study its ability to predict future actions and model the behaviour distribution at an individual-level and at a group level. We show that our method can match and outperform standard deep learning architectures and generate more realistic data, while using fewer parameters and providing increased interpretability.

PDF

IJCAI Conference 2024 Conference Paper

Large Language Models Are Not Strong Abstract Reasoners

Gaël Gendron
Qiming Bao
Michael Witbrock
Gillian Dobbie

Large Language Models have shown tremendous performance on a large variety of natural language processing tasks, ranging from text comprehension to common sense reasoning. However, the mechanisms responsible for this success remain opaque, and it is unclear whether LLMs can achieve human-like cognitive capabilities or whether these models are still fundamentally circumscribed. Abstract reasoning is a fundamental task for cognition, consisting of finding and applying a general pattern from few data. Evaluating deep neural architectures on this task could give insight into their potential limitations regarding reasoning and their broad generalisation abilities, yet this is currently an under-explored area. In this paper, we introduce a new benchmark for evaluating language models beyond memorization on abstract reasoning tasks. We perform extensive evaluations of state-of-the-art LLMs, showing that they currently achieve very limited performance in contrast with other natural language tasks, even when applying techniques that have been shown to improve performance on other NLP tasks. We argue that guiding LLM generation to follow causal paths could help improve the generalisation and reasoning abilities of LLMs.

PDF Details DOI

ECAI Conference 2024 Conference Paper

Learning After Learning: Positive Backward Transfer in Continual Learning

Wernsen Wong
Yun Sing Koh
Gillian Dobbie

Continual Learning (CL) methods enable models to learn new tasks without forgetting previously learned ones. Catastrophic Forgetting (CF) occurs when the parameters of a neural network are updated for a new task, causing the model to lose performance on tasks it has previously learned. To mitigate CF, parameter isolation methods use a “task mask” to allocate a subset of weights to each task; these weights are typically frozen to preserve task performance. However, frozen weights can limit positive backward transfer, which is the beneficial reuse of knowledge from new tasks to improve the accuracy of previously learned tasks. To address this gap, we introduce LEarning AFter learning (LEAF), a novel CL method that enables positive backward transfer by dynamically updating frozen task masks based on gradient updates that signal sufficient backward knowledge transfer. This mechanism allows for selective integration of new knowledge without sacrificing previously acquired knowledge. Our experiments show that LEAF surpasses existing state-of-the-art methods in terms of accuracy while maintaining comparable memory and runtime efficiencies. Moreover, it outperforms other backward transfer techniques in improving the accuracy of a prioritized task. Our code is available at https: //github. com/wernse/LEAF.

Details

AAAI Conference 2024 Conference Paper

Symmetric Self-Paced Learning for Domain Generalization

Di Zhao
Yun Sing Koh
Gillian Dobbie
Hongsheng Hu
Philippe Fournier-Viger

Deep learning methods often suffer performance degradation due to domain shift, where discrepancies exist between training and testing data distributions. Domain generalization mitigates this problem by leveraging information from multiple source domains to enhance model generalization capabilities for unseen domains. However, existing domain generalization methods typically present examples to the model in a random manner, overlooking the potential benefits of structured data presentation. To bridge this gap, we propose a novel learning strategy, Symmetric Self-Paced Learning (SSPL), for domain generalization. SSPL consists of a Symmetric Self-Paced training scheduler and a Gradient-based Difficulty Measure (GDM). Specifically, the proposed training scheduler initially focuses on easy examples, gradually shifting emphasis to harder examples as training progresses. GDM dynamically evaluates example difficulty through the gradient magnitude with respect to the example itself. Experiments across five popular benchmark datasets demonstrate the effectiveness of the proposed learning strategy.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Disentanglement of Latent Representations via Causal Interventions

Gaël Gendron
Michael Witbrock
Gillian Dobbie

The process of generating data such as images is controlled by independent and unknown factors of variation. The retrieval of these variables has been studied extensively in the disentanglement, causal representation learning, and independent component analysis fields. Recently, approaches merging these domains together have shown great success. Instead of directly representing the factors of variation, the problem of disentanglement can be seen as finding the interventions on one image that yield a change to a single factor. Following this assumption, we introduce a new method for disentanglement inspired by causal dynamics that combines causality theory with vector-quantized variational autoencoders. Our model considers the quantized vectors as causal variables and links them in a causal graph. It performs causal interventions on the graph and generates atomic transitions affecting a unique factor of variation in the image. We also introduce a new task of action retrieval that consists of finding the action responsible for the transition between two images. We test our method on standard synthetic and real-world disentanglement datasets. We show that it can effectively disentangle the factors of variation and perform precise interventions on high-level semantic attributes of an image without affecting its quality, even with imbalanced data distributions.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Membership Inference via Backdooring

Hongsheng Hu
Zoran Salčić
Gillian Dobbie
Jinjun Chen
Lichao Sun
Xuyun Zhang

Recently issued data privacy regulations like GDPR (General Data Protection Regulation) grant individuals the right to be forgotten. In the context of machine learning, this requires a model to forget about a training data sample if requested by the data owner (i. e. , machine unlearning). As an essential step prior to machine unlearning, it is still a challenge for a data owner to tell whether or not her data have been used by an unauthorized party to train a machine learning model. Membership inference is a recently emerging technique to identify whether a data sample was used to train a target model, and seems to be a promising solution to this challenge. However, straightforward adoption of existing membership inference approaches fails to address the challenge effectively due to being originally designed for attacking membership privacy and suffering from several severe limitations such as low inference accuracy on well-generalized models. In this paper, we propose a novel membership inference approach inspired by the backdoor technology to address the said challenge. Specifically, our approach of Membership Inference via Backdooring (MIB) leverages the key observation that a backdoored model behaves very differently from a clean model when predicting on deliberately marked samples created by a data owner. Appealingly, MIB requires data owners' marking a small number of samples for membership inference and only black-box access to the target model, with theoretical guarantees for inference results. We perform extensive experiments on various datasets and deep neural network architectures, and the results validate the efficacy of our approach, e. g. , marking only 0. 1% of the training dataset is practically sufficient for effective membership inference.

PDF Details DOI