Publications

Do GNNs also memorize their training data? Why are only certain nodes memorized? How do you explain the emergence of memorization in GNNs? How to mitigate memorization in GNNs? Stay Tuned to find out more :P

Graph rewiring methods have emerged as a powerful technique to address over-squashing and over-smoothing in Graph Neural Networks (GNNs). However, the underlying mechanisms that drive their effectiveness remain poorly understood. In this work, we investigate why spectral gap maximization works as a rewiring objective and under what conditions it may fail. We show that maximizing the spectral gap is not always beneficial and introduce a novel framework that leverages both community structure and feature similarity to guide graph rewiring.

We introduce the Braess Paradox in the context of Graph Neural Networks for the first time, showing that adding edges to a graph can actually hurt performance. Building on this insight, we propose a novel spectral graph pruning strategy that simultaneously addresses over-squashing and over-smoothing. Our method not only improves GNN performance but also discovers graph lottery tickets - sparse subgraphs that maintain or exceed the performance of the full graph.

This paper investigates the effect of adversarial perturbations on the hyperbolicity of graphs. Learning low-dimensional embeddings of graph data in certain curved Riemannian manifolds has recently gained traction due to their desirable property of acting as useful geometrical inductive biases. More specifically, models of Hyperbolic geometry such as Poincare Ball and Hyperboloid Model have found extensive applications for learning representations of discrete data such as Graphs and Trees with hierarchical anatomy. The hyperbolicity concept indicates whether the graph data under consideration is suitable for embedding in hyperbolic geometry. Lower values of hyperbolicity imply distortion-free embedding in hyperbolic space. We study adversarial perturbations that attempt to poison the graph structure, consequently rendering hyperbolic geometry an ineffective choice for learning representations. To circumvent this problem, we advocate for utilizing Lorentzian manifolds in machine learning pipelines and empirically show they are better suited to learn hierarchical relationships. Despite the recent proliferation of adversarial robustness methods in the graph data, this is the first work that explores the relationship between adversarial attacks and hyperbolicity property while also providing resolution to navigate such vulnerabilities.

In this paper we propose a novel deep learning framework to enhance underwater images by augmenting our network with wavelet corrected transformations. Wavelet transforms have recently made way into deep learning frameworks and their ability to reconstruct arbitrary signals accurately makes them favourable for many applications. Underwater images are subjected to unique distortions, this is mainly attributed to the fact that red wavelength light gets absorbed dominantly giving a greenish, blue hue. This wavelength dependent selective absorption of light and also scattering by the suspended particles introduce non-linear distortions that affect the quality of the images. We propose an encoder-decoder module with wavelet pooling and unpooling as one of the network components to perform progressive whitening and coloring transforms to enhance underwater images via realistic style transfer. We give a sound theoretical proof as to why wavelet transforms are better for signal reconstruction. We demonstrate our proposed framework on popular underwater images dataset and evaluate it using metrics like SSIM, PSNR and UCIQE and show that we achieve state-of-the-art results compared to those mentioned in the literature.

In this paper we propose a multi-scale video prediction framework with adversarial training for detecting anomalies in videos. Anomalous events are those which do not conform to normal behavior. Supervised learning framework cannot account for all the unusual activities since a universal definition of anomaly cannot be adopted. To tackle this problem, we propose an unsupervised approach to learn the internal representation of videos and use this learning to accurately predict the future-frames of the videos. We train our network adversarially on videos consisting of only normal activities. When our network encounters unusual or irregular activities the generated frames consists of fuzzy regions where the irregular activities are present. These fuzzy regions consequently lower the peak signal to noise ratio (PSNR) of the generated frames. The PSNR values are normalized to have values between 0 and 1 and is used as a regularity score to tag a frame as anomalous or not-anomalous. We provide quantitative and qualitative evaluation of the proposed framework and also introduce Earth Mover's Distance as a new evaluation metric to assess the quality of the images generated. We demonstrate our framework on UCSD Pedestrian dataset and show that we achieve comparable results.