Sayan Ranu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sayan Ranu has a total of 109 co-authors. Here are the top co-authors by number of shared publications:
- Naduvath Mana Anoop Krishnan
Department of Civil Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India
5 shared publications - Arnab Bhattacharya
Indian Institute of Technology Kanpur India
4 shared publications - Sahil Manchanda
Department of Computer Science and Engineering Indian Institute of Technology Delhi
4 shared publications - Ambuj Singh
UC Santa Barbara, Santa Barbara, CA, USA
3 shared publications - Amitabha Bagchi
Indian Institute of Technology Delhi, Delhi, Delhi, India
3 shared publications - Sahil Manchanda
AI Garage, Mastercard, Gurgaon, Haryana, India
3 shared publications
Latest Publications
- Open Access
- 1 October 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (5) , 055049
Learnable coarsening for two-phase flow in porous media
Hydrodynamic simulations of multi-phase flow in porous media are essential for oil production forecasting but require significant computational resources. Traditional approaches lead to high memory and time demands, restricting multi-scenario analysis. We propose a learnable coarsening algorithm based on graph neural networks (GNNs) with node aggregation for 2D two-phase flow modeling. The coarsened grid adapts to the reservoir geometry, its properties, and production data. Our algorithm is integrated with a graph-based finite volume method (FVM) solver, differentiable Voronoi tessellation, and a fully implicit upwind scheme. The unstructured computational grid is modeled as a graph with cell centers, adjacency edges, and a rich set of node features: coordinates, permeability, masks, distances to wells, permeability gradients, and wells influence potential. GNN produces soft assignments for probabilistic clustering, preserving wells and sensors. Training employs an FVM solver with physics-informed loss matching saturation and production rate time series at wells, promoting grid uniformity. Extending our prior works, our method enables coarsening by 10 times with relative error of about 1%–2%, accurately reproducing saturation fields, oil production, and water breakthrough on synthetic and realistic permeability fields.
- 1 October 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (5) , 055049
Open AccessLearnable coarsening for two-phase flow in porous media
Hydrodynamic simulations of multi-phase flow in porous media are essential for oil production forecasting but require significant computational resources. Traditional approaches lead to high memory and time demands, restricting multi-scenario analysis. We propose a learnable coarsening algorithm based on graph neural networks (GNNs) with node aggregation for 2D two-phase flow modeling. The coarsened grid adapts to the reservoir geometry, its properties, and production data. Our algorithm is integrated with a graph-based finite volume method (FVM) solver, differentiable Voronoi tessellation, and a fully implicit upwind scheme. The unstructured computational grid is modeled as a graph with cell centers, adjacency edges, and a rich set of node features: coordinates, permeability, masks, distances to wells, permeability gradients, and wells influence potential. GNN produces soft assignments for probabilistic clustering, preserving wells and sensors. Training employs an FVM solver with physics-informed loss matching saturation and production rate time series at wells, promoting grid uniformity. Extending our prior works, our method enables coarsening by 10 times with relative error of about 1%–2%, accurately reproducing saturation fields, oil production, and water breakthrough on synthetic and realistic permeability fields.
- Open Access
- 30 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 598-599
FinDS: Workshop on Data Management for the Modern Financial Systems
- 30 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 598-599
Open AccessFinDS: Workshop on Data Management for the Modern Financial Systems
- Open Access
- 6 January 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (1)
Learnable stability-aware computational grid coarsening for accelerating physics simulations
Efficient simulations of complex physical systems described by partial differential equations (PDE) require computational methods that can reduce the resource demands without sacrificing the accuracy. Here, we introduce a framework based on graph neural networks (GNN) for learnable self-supervised differentiable coarsening of unstructured computational grids. We leverage graph-based representation of the physical system and offer a computational grid coarsening method which preserves the underlying physical properties together with the stability of the chosen numerical scheme with the help of the designed loss terms. The coarsening model is trained in a self-supervised way by minimizing the error between the output of the simulations on the coarsened and original grids.We evaluate the approach on four PDE systems of different types, covering both linear and nonlinear regimes, including subsurface flow and wave propagation. We demonstrate that the proposed framework exhibits the ability to maintain high fidelity in simulation outputs even after 95% reduction in the number of nodes, significantly reducing computational overhead. We show that the model exhibits generalizability to unseen scenarios, thereby outperforming the baselines. The generality of the developed framework is also proven by its possibility to adapt to implicit numerical schemes used to model stiff systems of PDEs. Thus, the developed approach demonstrates the ability to accelerate physical simulations without compromising accuracy.
- 6 January 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (1)
Open AccessLearnable stability-aware computational grid coarsening for accelerating physics simulations
Efficient simulations of complex physical systems described by partial differential equations (PDE) require computational methods that can reduce the resource demands without sacrificing the accuracy. Here, we introduce a framework based on graph neural networks (GNN) for learnable self-supervised differentiable coarsening of unstructured computational grids. We leverage graph-based representation of the physical system and offer a computational grid coarsening method which preserves the underlying physical properties together with the stability of the chosen numerical scheme with the help of the designed loss terms. The coarsening model is trained in a self-supervised way by minimizing the error between the output of the simulations on the coarsened and original grids.We evaluate the approach on four PDE systems of different types, covering both linear and nonlinear regimes, including subsurface flow and wave propagation. We demonstrate that the proposed framework exhibits the ability to maintain high fidelity in simulation outputs even after 95% reduction in the number of nodes, significantly reducing computational overhead. We show that the model exhibits generalizability to unseen scenarios, thereby outperforming the baselines. The generality of the developed framework is also proven by its possibility to adapt to implicit numerical schemes used to model stiff systems of PDEs. Thus, the developed approach demonstrates the ability to accelerate physical simulations without compromising accuracy.
- Open Access
- 18 August 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 16 (5) , 1-23
GCFExplainer: Global Counterfactual Explainer for Graph Neural Networks
Graph neural networks (GNNs) find applications in various domains such as computational biology, natural language processing, and computer security. Owing to their popularity, there is an increasing need to explain GNN predictions since GNNs are black-box machine learning models. One way to address this issue involves using counterfactual reasoning where the objective is to alter the GNN prediction by minimal changes in the input graph. Existing methods for counterfactual explanation of GNNs are limited to instance-specific local reasoning. This approach has two major limitations of not being able to offer global recourse policies and overloading human cognitive ability with too much information. In this work, we study the global explainability of GNNs through global counterfactual reasoning. Specifically, we want to find a small set of representative counterfactual graphs that explains all input graphs. Toward this goal, we propose GCFExplainer , a novel algorithm powered by vertex-reinforced random walks on an edit map of graphs with a greedy summary . Extensive experiments on real graph datasets show that the global explanation from GCFExplainer provides important high-level insights of the model behavior and achieves a 46.9% gain in recourse coverage, a 9.5% reduction in recourse cost compared to the state-of-the-art local counterfactual explainers. We also demonstrate that GCFExplainer generates explanations that are more consistent with input dataset characteristics, and is robust under adversarial attacks. In addition, K-GCFExplainer , which incorporates a graph clustering component into GCFExplainer , is introduced as a more competitive extension for datasets with a clustering structure, leading to superior performance in three out of four datasets in the experiments and better scalability.
- 18 August 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 16 (5) , 1-23
Open AccessGCFExplainer: Global Counterfactual Explainer for Graph Neural Networks
Graph neural networks (GNNs) find applications in various domains such as computational biology, natural language processing, and computer security. Owing to their popularity, there is an increasing need to explain GNN predictions since GNNs are black-box machine learning models. One way to address this issue involves using counterfactual reasoning where the objective is to alter the GNN prediction by minimal changes in the input graph. Existing methods for counterfactual explanation of GNNs are limited to instance-specific local reasoning. This approach has two major limitations of not being able to offer global recourse policies and overloading human cognitive ability with too much information. In this work, we study the global explainability of GNNs through global counterfactual reasoning. Specifically, we want to find a small set of representative counterfactual graphs that explains all input graphs. Toward this goal, we propose GCFExplainer , a novel algorithm powered by vertex-reinforced random walks on an edit map of graphs with a greedy summary . Extensive experiments on real graph datasets show that the global explanation from GCFExplainer provides important high-level insights of the model behavior and achieves a 46.9% gain in recourse coverage, a 9.5% reduction in recourse cost compared to the state-of-the-art local counterfactual explainers. We also demonstrate that GCFExplainer generates explanations that are more consistent with input dataset characteristics, and is robust under adversarial attacks. In addition, K-GCFExplainer , which incorporates a graph clustering component into GCFExplainer , is introduced as a more competitive extension for datasets with a clustering structure, leading to superior performance in three out of four datasets in the experiments and better scalability.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2859-2870
TAG2M - A Task-Agnostic Knowledge Distillation Framework for Distilling GNN to MLP
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2859-2870
Open AccessTAG2M - A Task-Agnostic Knowledge Distillation Framework for Distilling GNN to MLP
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2315-2325
Alpine: Partial Unlabeled Graph Alignment
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2315-2325
Open AccessAlpine: Partial Unlabeled Graph Alignment
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 778-789
Persona Identification in E-Commerce with Scarce Labels and In-Context Graph Learning
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 778-789
Open AccessPersona Identification in E-Commerce with Scarce Labels and In-Context Graph Learning
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 2584-2595
NeuroCut: A Neural Approach for Robust Graph Partitioning
Graph partitioning aims to divide a graph into k disjoint subsets while optimizing a specific partitioning objective. The majority of formulations related to graph partitioning exhibit NP-hardness due to their combinatorial nature. Conventional methods, like approximation algorithms or heuristics, are designed for distinct partitioning objectives and fail to achieve generalization across other important partitioning objectives. Recently machine learning-based methods have been developed that learn directly from data. Further, these methods have a distinct advantage of utilizing node features that carry additional information. However, these methods assume differentiability of target partitioning objective functions and cannot generalize for an unknown number of partitions, i.e., they assume the number of partitions is provided in advance. In this study, we develop NeuroCut with two key innovations over previous methodologies. First, by leveraging a reinforcement learning-based framework over node representations derived from a graph neural network and positional features, NeuroCut can accommodate any optimization objective, even those with non-differentiable functions. Second, we decouple the parameter space and the partition count making NeuroCut inductive to any unseen number of partition, which is provided at query time. Through empirical evaluation, we demonstrate that NeuroCut excels in identifying high-quality partitions, showcases strong generalization across a wide spectrum of partitioning objectives, and exhibits strong generalization to unseen partition count.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 2584-2595
Open AccessNeuroCut: A Neural Approach for Robust Graph Partitioning
Graph partitioning aims to divide a graph into k disjoint subsets while optimizing a specific partitioning objective. The majority of formulations related to graph partitioning exhibit NP-hardness due to their combinatorial nature. Conventional methods, like approximation algorithms or heuristics, are designed for distinct partitioning objectives and fail to achieve generalization across other important partitioning objectives. Recently machine learning-based methods have been developed that learn directly from data. Further, these methods have a distinct advantage of utilizing node features that carry additional information. However, these methods assume differentiability of target partitioning objective functions and cannot generalize for an unknown number of partitions, i.e., they assume the number of partitions is provided in advance. In this study, we develop NeuroCut with two key innovations over previous methodologies. First, by leveraging a reinforcement learning-based framework over node representations derived from a graph neural network and positional features, NeuroCut can accommodate any optimization objective, even those with non-differentiable functions. Second, we decouple the parameter space and the partition count making NeuroCut inductive to any unseen number of partition, which is provided at query time. Through empirical evaluation, we demonstrate that NeuroCut excels in identifying high-quality partitions, showcases strong generalization across a wide spectrum of partitioning objectives, and exhibits strong generalization to unseen partition count.
- Open Access
Mirage: Model-Agnostic Graph Distillation for Graph Classification
GNNs, like other deep learning models, are data and computation hungry. There is a pressing need to scale training of GNNs on large datasets to enable their usage on low-resource environments. Graph distillation is an effort in that direction with the aim to construct a smaller synthetic training set from the original training data without significantly compromising model performance. While initial efforts are promising, this work is motivated by two key observations: (1) Existing graph distillation algorithms themselves rely on training with the full dataset, which undermines the very premise of graph distillation. (2) The distillation process is specific to the target GNN architecture and hyper-parameters and thus not robust to changes in the modeling pipeline. We circumvent these limitations by designing a distillation algorithm called Mirage for graph classification. Mirage is built on the insight that a message-passing GNN decomposes the input graph into a multiset of computation trees. Furthermore, the frequency distribution of computation trees is often skewed in nature, enabling us to condense this data into a concise distilled summary. By compressing the computation data itself, as opposed to emulating gradient flows on the original training set-a prevalent approach to date-Mirage transforms into an unsupervised and architecture-agnostic distillation algorithm. Extensive benchmarking on real-world datasets underscores Mirage's superiority, showcasing enhanced generalization accuracy, data compression, and distillation efficiency when compared to state-of-the-art baselines.
Open AccessMirage: Model-Agnostic Graph Distillation for Graph Classification
GNNs, like other deep learning models, are data and computation hungry. There is a pressing need to scale training of GNNs on large datasets to enable their usage on low-resource environments. Graph distillation is an effort in that direction with the aim to construct a smaller synthetic training set from the original training data without significantly compromising model performance. While initial efforts are promising, this work is motivated by two key observations: (1) Existing graph distillation algorithms themselves rely on training with the full dataset, which undermines the very premise of graph distillation. (2) The distillation process is specific to the target GNN architecture and hyper-parameters and thus not robust to changes in the modeling pipeline. We circumvent these limitations by designing a distillation algorithm called Mirage for graph classification. Mirage is built on the insight that a message-passing GNN decomposes the input graph into a multiset of computation trees. Furthermore, the frequency distribution of computation trees is often skewed in nature, enabling us to condense this data into a concise distilled summary. By compressing the computation data itself, as opposed to emulating gradient flows on the original training set-a prevalent approach to date-Mirage transforms into an unsupervised and architecture-agnostic distillation algorithm. Extensive benchmarking on real-world datasets underscores Mirage's superiority, showcasing enhanced generalization accuracy, data compression, and distillation efficiency when compared to state-of-the-art baselines.
- Open Access
GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
Numerous explainability methods have been proposed to shed light on the inner workings of GNNs. Despite the inclusion of empirical evaluations in all the proposed algorithms, the interrogative aspects of these evaluations lack diversity. As a result, various facets of explainability pertaining to GNNs, such as a comparative analysis of counterfactual reasoners, their stability to variational factors such as different GNN architectures, noise, stochasticity in non-convex loss surfaces, feasibility amidst domain constraints, and so forth, have yet to be formally investigated. Motivated by this need, we present a benchmarking study on perturbation-based explainability methods for GNNs, aiming to systematically evaluate and compare a wide range of explainability techniques. Among the key findings of our study, we identify the Pareto-optimal methods that exhibit superior efficacy and stability in the presence of noise. Nonetheless, our study reveals that all algorithms are affected by stability issues when faced with noisy data. Furthermore, we have established that the current generation of counterfactual explainers often fails to provide feasible recourses due to violations of topological constraints encoded by domain-specific considerations. Overall, this benchmarking study empowers stakeholders in the field of GNNs with a comprehensive understanding of the state-of-the-art explainability methods, potential research problems for further enhancement, and the implications of their application in real-world scenarios.
Open AccessGNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
Numerous explainability methods have been proposed to shed light on the inner workings of GNNs. Despite the inclusion of empirical evaluations in all the proposed algorithms, the interrogative aspects of these evaluations lack diversity. As a result, various facets of explainability pertaining to GNNs, such as a comparative analysis of counterfactual reasoners, their stability to variational factors such as different GNN architectures, noise, stochasticity in non-convex loss surfaces, feasibility amidst domain constraints, and so forth, have yet to be formally investigated. Motivated by this need, we present a benchmarking study on perturbation-based explainability methods for GNNs, aiming to systematically evaluate and compare a wide range of explainability techniques. Among the key findings of our study, we identify the Pareto-optimal methods that exhibit superior efficacy and stability in the presence of noise. Nonetheless, our study reveals that all algorithms are affected by stability issues when faced with noisy data. Furthermore, we have established that the current generation of counterfactual explainers often fails to provide feasible recourses due to violations of topological constraints encoded by domain-specific considerations. Overall, this benchmarking study empowers stakeholders in the field of GNNs with a comprehensive understanding of the state-of-the-art explainability methods, potential research problems for further enhancement, and the implications of their application in real-world scenarios.