Tapabrata Chakraborti

Robin Mitra, Sarah F. McGough, Tapabrata Chakraborti et al. · oxford

Missing data are an unavoidable complication in many machine learning tasks. When data are `missing at random' there exist a range of tools and techniques to deal with the issue. However, as machine learning studies become more ambitious, and seek to learn from ever-larger volumes of heterogeneous data, an increasingly encountered problem arises in which missing values exhibit an association or structure, either explicitly or implicitly. Such `structured missingness' raises a range of challenges that have not yet been systematically addressed, and presents a fundamental hindrance to machine learning at scale. Here, we outline the current literature and propose a set of grand challenges in learning from data with structured missingness.

Saswata Bose, Suvadeep Maiti, Shivam Kumar Sharma et al.

Accurate sleep staging is essential for diagnosing OSA and hypopnea in stroke patients. Although PSG is reliable, it is costly, labor-intensive, and manually scored. While deep learning enables automated EEG-based sleep staging in healthy subjects, our analysis shows poor generalization to clinical populations with disrupted sleep. Using Grad-CAM interpretations, we systematically demonstrate this limitation. We introduce iSLEEPS, a newly clinically annotated ischemic stroke dataset (to be publicly released), and evaluate a SE-ResNet plus bidirectional LSTM model for single-channel EEG sleep staging. As expected, cross-domain performance between healthy and diseased subjects is poor. Attention visualizations, supported by clinical expert feedback, show the model focuses on physiologically uninformative EEG regions in patient data. Statistical and computational analyses further confirm significant sleep architecture differences between healthy and ischemic stroke cohorts, highlighting the need for subject-aware or disease-specific models with clinical validation before deployment. A summary of the paper and the code is available at https://himalayansaswatabose.github.io/iSLEEPS_Explainability.github.io/

Samiran Dey, Christopher R. S. Banerji, Partha Basuchowdhuri et al.

Emerging research has highlighted that artificial intelligence based multimodal fusion of digital pathology and transcriptomic features can improve cancer diagnosis (grading/subtyping) and prognosis (survival risk) prediction. However, such direct fusion for joint decision is impractical in real clinical settings, where histopathology is still the gold standard for diagnosis and transcriptomic tests are rarely requested, at least in the public healthcare system. With our novel diffusion based crossmodal generative AI model PathGen, we show that genomic expressions synthesized from digital histopathology jointly predicts cancer grading and patient survival risk with high accuracy (state-of-the-art performance), certainty (through conformal coverage guarantee) and interpretability (through distributed attention maps). PathGen code is available for open use by the research community through GitHub at https://github.com/Samiran-Dey/PathGen.

Enrico Parisini, Tapabrata Chakraborti, Chris Harbron et al.

Concept Bottleneck Models aim to improve interpretability by predicting high-level intermediate concepts, representing a promising approach for deployment in high-risk scenarios. However, they are known to suffer from information leakage, whereby models exploit unintended information encoded within the learned concepts. We introduce an information-theoretic framework to rigorously characterise and quantify leakage, and define two complementary measures: the concepts-task leakage (CTL) and interconcept leakage (ICL) scores. We show that these measures are strongly predictive of model behaviour under interventions and outperform existing alternatives in robustness and reliability. Using this framework, we identify the primary causes of leakage and provide strong evidence that Concept Embedding Models exhibit substantial leakage regardless of the hyperparameters choice. Finally, we propose practical guidelines for designing concept-based models to reduce leakage and ensure interpretability.

Anthony Baptista, Alessandro Barp, Tapabrata Chakraborti et al.

Deep neural networks (DNNs) are powerful tools for approximating the distribution of complex data. It is known that data passing through a trained DNN classifier undergoes a series of geometric and topological simplifications. While some progress has been made toward understanding these transformations in neural networks with smooth activation functions, an understanding in the more general setting of non-smooth activation functions, such as the rectified linear unit (ReLU), which tend to perform better, is required. Here we propose that the geometric transformations performed by DNNs during classification tasks have parallels to those expected under Hamilton's Ricci flow - a tool from differential geometry that evolves a manifold by smoothing its curvature, in order to identify its topology. To illustrate this idea, we present a computational framework to quantify the geometric changes that occur as data passes through successive layers of a DNN, and use this framework to motivate a notion of `global Ricci network flow' that can be used to assess a DNN's ability to disentangle complex data geometries to solve classification problems. By training more than $1,500$ DNN classifiers of different widths and depths on synthetic and real-world data, we show that the strength of global Ricci network flow-like behaviour correlates with accuracy for well-trained DNNs, independently of depth, width and data set. Our findings motivate the use of tools from differential and discrete geometry to the problem of explainability in deep learning.

Swarnava Bhattacharyya, Umapada Pal, Tapabrata Chakraborti · oxford

Deep learning based diagnostic AI systems based on medical images are starting to provide similar performance as human experts. However these data hungry complex systems are inherently black boxes and therefore slow to be adopted for high risk applications like healthcare. This problem of lack of transparency is exacerbated in the case of recent large foundation models, which are trained in a self supervised manner on millions of data points to provide robust generalisation across a range of downstream tasks, but the embeddings generated from them happen through a process that is not interpretable, and hence not easily trustable for clinical applications. To address this timely issue, we deploy conformal analysis to quantify the predictive uncertainty of a vision transformer (ViT) based foundation model across patient demographics with respect to sex, age and ethnicity for the tasks of skin lesion classification using several public benchmark datasets. The significant advantage of this method is that conformal analysis is method independent and it not only provides a coverage guarantee at population level but also provides an uncertainty score for each individual. We used a model-agnostic dynamic F1-score-based sampling during model training, which helped to stabilize the class imbalance and we investigate the effects on uncertainty quantification (UQ) with or without this bias mitigation step. Thus we show how this can be used as a fairness metric to evaluate the robustness of the feature embeddings of the foundation model (Google DermFoundation) and thus advance the trustworthiness and fairness of clinical AI.

Prantik Deb, Srimanth Dhondy, N. Ramakrishna et al.

Chest X-ray (CXR) segmentation is an important step in computer-aided diagnosis, yet deploying large foundation models in clinical settings remains challenging due to computational constraints. We propose AdaLoRA-QAT, a two-stage fine-tuning framework that combines adaptive low-rank encoder adaptation with full quantization-aware training. Adaptive rank allocation improves parameter efficiency, while selective mixed-precision INT8 quantization preserves structural fidelity crucial for clinical reliability. Evaluated across large-scale CXR datasets, AdaLoRA-QAT achieves 95.6% Dice, matching full-precision SAM decoder fine-tuning while reducing trainable parameters by 16.6\times and yielding 2.24\times model compression. A Wilcoxon signed-rank test confirms that quantization does not significantly degrade segmentation accuracy. These results demonstrate that AdaLoRA-QAT effectively balances accuracy, efficiency, and structural trust-worthiness, enabling compact and deployable foundation models for medical image segmentation. Code and pretrained models are available at: https://prantik-pdeb.github.io/adaloraqat.github.io/

Zihan Wei, Tapabrata Chakraborti · oxford

Recent works have shown that deep learning based skin lesion image classification models trained on unbalanced dataset can exhibit bias toward protected demographic attributes such as race, age,and gender. Current bias mitigation methods usually either achieve high level of fairness with the degradation of accuracy, or only improve the model fairness on a single attribute. Additionally usually most bias mitigation strategies are either pre hoc through data processing or post hoc through fairness evaluation, instead of being integrated into the model learning itself. To solve these existing drawbacks, we propose a new Individual Typology Angle (ITA) Loss-based skin tone normalization and data augmentation method that directly feeds into an adaptable meta learning-based joint channel pruning framework. In skin tone normalization, ITA is used to estimate skin tone type and adjust automatically to target tones for dataset balancing. In the joint channel pruning framework, two nested optimization loops are used to find critical channels.The inner optimization loop finds and prunes the local critical channels by weighted soft nearest neighbor loss, and the outer optimization loop updates the weight of each attribute using group wise variance loss on meta-set. Experiments conducted in the ISIC2019 dataset validate the effectiveness of our method in simultaneously improving the fairness of the model on multiple sensitive attributes without significant degradation of accuracy. Finally, although the pruning mechanism adds some computational cost during training phase, usually training is done off line. More importantly,

Lalith Bharadwaj Baru, Kamalaker Dadi, Tapabrata Chakraborti et al. · oxford

Accurate segmentation of medical images is challenging due to unclear lesion boundaries and mask variability. We introduce \emph{Segmentation Schödinger Bridge (SSB)}, the first application of Schödinger Bridge for ambiguous medical image segmentation, modelling joint image-mask dynamics to enhance performance. SSB preserves structural integrity, delineates unclear boundaries without additional guidance, and maintains diversity using a novel loss function. We further propose the \emph{Diversity Divergence Index} ($D_{DDI}$) to quantify inter-rater variability, capturing both diversity and consensus. SSB achieves state-of-the-art performance on LIDC-IDRI, COCA, and RACER (in-house) datasets.

Youssef Abdalla, Marrisa Taub, Eleanor Hilton et al. · oxford

Data scarcity in pharmaceutical research has led to reliance on labour-intensive trial-and-error approaches for development rather than data-driven methods. While Machine Learning offers a solution, existing datasets are often small and noisy, limiting their utility. To address this, we developed a Variationally Encoded Conditional Tabular Generative Adversarial Network (VECT-GAN), a novel generative model specifically designed for augmenting small, noisy datasets. We introduce a pipeline where data is augmented before regression model development and demonstrate that this consistently and significantly improves performance over other state-of-the-art tabular generative models. We apply this pipeline across six pharmaceutical datasets, and highlight its real-world applicability by developing novel polymers with medically desirable mucoadhesive properties, which we made and experimentally characterised. Additionally, we pre-train the model on the ChEMBL database of drug-like molecules, leveraging knowledge distillation to enhance its generalisability, making it readily available for use on pharmaceutical datasets containing small molecules, an extremely common pharmaceutical task. We demonstrate the power of synthetic data for regularising small tabular datasets, highlighting its potential to become standard practice in pharmaceutical model development, and make our method, including VECT-GAN pre-trained on ChEMBL available as a pip package.

Tapabrata Chakraborti, Arijit Patra, Alison Noble

Was it fair that Harry was hired but not Barry? Was it fair that Pam was fired instead of Sam? How can one ensure fairness when an intelligent algorithm takes these decisions instead of a human? How can one ensure that the decisions were taken based on merit and not on protected attributes like race or sex? These are the questions that must be answered now that many decisions in real life can be made through machine learning. However research in fairness of algorithms has focused on the counterfactual questions "what if?" or "why?", whereas in real life most subjective questions of consequence are contrastive: "why this but not that?". We introduce concepts and mathematical tools using causal inference to address contrastive fairness in algorithmic decision-making with illustrative examples.

Tapabrata Chakraborti, Brendan McCane, Steven Mills et al.

Any generic deep machine learning algorithm is essentially a function fitting exercise, where the network tunes its weights and parameters to learn discriminatory features by minimizing some cost function. Though the network tries to learn the optimal feature space, it seldom tries to learn an optimal distance metric in the cost function, and hence misses out on an additional layer of abstraction. We present a simple effective way of achieving this by learning a generic Mahalanabis distance in a collaborative loss function in an end-to-end fashion with any standard convolutional network as the feature learner. The proposed method DML-CRC gives state-of-the-art performance on benchmark fine-grained classification datasets CUB Birds, Oxford Flowers and Oxford-IIIT Pets using the VGG-19 deep network. The method is network agnostic and can be used for any similar classification tasks.

Tapabrata Chakraborti, Brendan McCane, Steven Mills et al.

We present a conditional probabilistic framework for collaborative representation of image patches. It incorporates background compensation and outlier patch suppression into the main formulation itself, thus doing away with the need for pre-processing steps to handle the same. A closed form non-iterative solution of the cost function is derived. The proposed method (PProCRC) outperforms earlier CRC formulations: patch based (PCRC, GP-CRC) as well as the state-of-the-art probabilistic (ProCRC and EProCRC) on three fine-grained species recognition datasets (Oxford Flowers, Oxford-IIIT Pets and CUB Birds) using two CNN backbones (Vgg-19 and ResNet-50).

Tapabrata Chakraborti, Brendan McCane, Steven Mills et al.

We present an end-to-end deep network for fine-grained visual categorization called Collaborative Convolutional Network (CoCoNet). The network uses a collaborative layer after the convolutional layers to represent an image as an optimal weighted collaboration of features learned from training samples as a whole rather than one at a time. This gives CoCoNet more power to encode the fine-grained nature of the data with limited samples. We perform a detailed study of the performance with 1-stage and 2-stage transfer learning. The ablation study shows that the proposed method outperforms its constituent parts consistently. CoCoNet also outperforms few state-of-the-art competing methods. Experiments have been performed on the fine-grained bird species classification problem as a representative example, but the method may be applied to other similar tasks. We also introduce a new public dataset for fine-grained species recognition, that of Indian endemic birds and have reported initial results on it.

Tapabrata Chakraborti, Brendan McCane, Steven Mills et al.

This letter introduces the LOOP binary descriptor (local optimal oriented pattern) that encodes rotation invariance into the main formulation itself. This makes any post processing stage for rotation invariance redundant and improves on both accuracy and time complexity. We consider fine-grained lepidoptera (moth/butterfly) species recognition as the representative problem since it involves repetition of localized patterns and textures that may be exploited for discrimination. We evaluate the performance of LOOP against its predecessors as well as few other popular descriptors. Besides experiments on standard benchmarks, we also introduce a new small image dataset on NZ Lepidoptera. Loop performs as well or better on all datasets evaluated compared to previous binary descriptors. The new dataset and demo code of the proposed method are to be made available through the lead author's academic webpage and GitHub.