Author name cluster

Ahmed Abbas

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.

4 papers

2 author rows

AAAI Conference 2024 Conference Paper

DOGE-Train: Discrete Optimization on GPU with End-to-End Training

Ahmed Abbas
Paul Swoboda

We present a fast, scalable, data-driven approach for solving relaxations of 0-1 integer linear programs. We use a combination of graph neural networks (GNN) and a Lagrange decomposition based algorithm. We make the latter differentiable for end-to-end training and use GNNs to predict its algorithmic parameters. This allows to retain the algorithm's theoretical properties including dual feasibility and guaranteed non-decrease in the lower bound while improving it via training. We overcome suboptimal fixed points of the basic solver by additional non-parametric GNN update steps maintaining dual feasibility. For training we use an unsupervised loss. We train on smaller problems and test on larger ones showing strong generalization performance with a GNN comprising only around 10k parameters. Our solver achieves significantly faster performance and better dual objectives than its non-learned version, achieving close to optimal objective values of LP relaxations of very large structured prediction problems and on selected combinatorial ones. In particular, we achieve better objective values than specialized approximate solvers for specific problem classes while retaining their efficiency. Our solver has better any-time performance over a large time period compared to a commercial solver.

PDF Details DOI

ICML Conference 2023 Conference Paper

ClusterFuG: Clustering Fully connected Graphs by Multicut

Ahmed Abbas
Paul Swoboda

We propose a graph clustering formulation based on multicut (a. k. a. weighted correlation clustering) on the complete graph. Our formulation does not need specification of the graph topology as in the original sparse formulation of multicut, making our approach simpler and potentially better performing. In contrast to unweighted correlation clustering we allow for a more expressive weighted cost structure. In dense multicut, the clustering objective is given in a factorized form as inner products of node feature vectors. This allows for an efficient formulation and inference in contrast to multicut/weighted correlation clustering, which has at least quadratic representation and computation complexity when working on the complete graph. We show how to rewrite classical greedy algorithms for multicut in our dense setting and how to modify them for greater efficiency and solution quality. In particular, our algorithms scale to graphs with tens of thousands of nodes. Empirical evidence on instance segmentation on Cityscapes and clustering of ImageNet datasets shows the merits of our approach.

Details

NeurIPS Conference 2021 Conference Paper

Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach

Ahmed Abbas
Paul Swoboda

We propose a fully differentiable architecture for simultaneous semantic and instance segmentation (a. k. a. panoptic segmentation) consisting of a convolutional neural network and an asymmetric multiway cut problem solver. The latter solves a combinatorial optimization problem that elegantly incorporates semantic and boundary predictions to produce a panoptic labeling. Our formulation allows to directly maximize a smooth surrogate of the panoptic quality metric by backpropagating the gradient through the optimization problem. Experimental evaluation shows improvement by backpropagating through the optimization problem w. r. t. comparable approaches on Cityscapes and COCO datasets. Overall, our approach of combinatorial optimization for panoptic segmentation (COPS) shows the utility of using optimization in tandem with deep learning in a challenging large scale real-world problem and showcases benefits and insights into training such an architecture.

PDF Details

YNICL Journal 2021 Journal Article

Evaluation of the early-phase [18F]AV45 PET as an optimal surrogate of [18F]FDG PET in ageing and Alzheimer’s clinical syndrome

Matthieu Vanhoutte
Brigitte Landeau
Siya Sherif
Vincent de La Sayette
Sophie Dautricourt
Ahmed Abbas
Alain Manrique
Anne Chocat

Dual-phase [18F]AV45 positron emission tomography (PET) is highly promising in the assessment of neurodegenerative diseases, allowing to obtain information on both neurodegeneration (early-phase; eAV45) and amyloid deposition (late-phase; lAV45) which are highly complementary; yet eAV45 needs further evaluation. This study aims at validating eAV45 as an optimal proxy of [18F]FDG PET in a large mixed-population of healthy ageing and Alzheimer’s clinical syndrome participants (n = 191) who had [18F]FDG PET, eAV45 and lAV45 scans. We found early time frame 0–4 min to give maximal correlation with [18F]FDG PET and minimal correlation with lAV45. Moreover, maximal overlap of [18F]FDG PET versus eAV45 associations with clinical diagnosis and cognition was obtained with pons scaling. Across reference regions, classification performance between clinical subgroups was similar for both eAV45 and [18F]FDG PET. These findings highlight the optimal use of eAV45 to assess neurodegeneration as a validated proxy of [18F]FDG PET. On top of this purpose, this study showed that combined [18F]AV45 PET dual-biomarker even outperformed [18F]FDG PET or lAV45 alone.

Details DOI