Author name cluster

Manohar Kaul

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.

7 papers

2 author rows

TMLR Journal 2026 Journal Article

Proper Orthogonal Decomposition for Scalable Training of Graph Neural Networks

Abhishek A
Manohar Kaul
Mohit Meena
Mahesh Chandran

As large-scale graphs become ubiquitous in real-world applications, there is growing concern about the memory and time requirement to train a graph neural network (GNN) model for such datasets. Storing the entire adjacency and node embedding matrices in memory is infeasible in such a scenario. Standard sampling-based methods for addressing the memory constraint suffer from the dependence of the number of mini-batches on the graph size. Existing sketch-based methods and graph compression techniques operate at higher sketch ratios, with the graph compression techniques showing poor generalization, implying that different GNNs trained on the same synthetic graph have performance gaps. Sketch-based methods necessitate online learning of sketches, further increasing the complexity. In this paper, we propose a new sketch-based algorithm, {PGNN}, employing the Proper Orthogonal Decomposition (POD) method to craft update rules to train GNNs, improving the memory requirement and training time without the complication of updating the sketches during training. Experiments on standard graph datasets show that {PGNN} can reach much lower sketch ratios without compromising the performance. We demonstrate that the POD projection matrix is provably optimal, minimizing an upper bound on the projection error induced by the linearized GNN (SGC) update rule. Empirical findings validate our approach, demonstrating superior performance at reduced sketch ratios and adaptability across various GNN architectures.

PDF Details

ICLR Conference 2025 Conference Paper

Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks

Manohar Kaul
Aditya Saibewar
Sadbhavana Babar

Recent jailbreak attempts on Large Language Models (LLMs) have shifted from algorithm-focused to human-like social engineering attacks, with persuasion-based techniques emerging as a particularly effective subset. These attacks evolve rapidly, demonstrate high creativity, and boast superior attack success rates. To combat such threats, we propose a promising approach to enhancing LLM safety by leveraging the underlying geometry of input prompt token embeddings using hypergraphs. This approach allows us to model the differences in information flow between benign and malicious LLM prompts. In our approach, each LLM prompt is represented as a metric hypergraph, forming a compact metric space. We then construct a higher-order metric space over these compact metric hypergraphs using the Gromov-Hausdorff distance as a generalized metric. Within this space of metric hypergraph spaces, our safety filter learns to classify between harmful and benign prompts. Our study presents theoretical guarantees on the classifier's generalization error for novel and unseen LLM input prompts. Extensive empirical evaluations demonstrate that our method significantly outperforms both existing state-of-the-art generic defense mechanisms and naive baselines. Notably, our approach also achieves comparable performance to specialized defenses against algorithm-focused attacks.

Details

ICLR Conference 2025 Conference Paper

Efficient Jailbreak Attack sequences on Large Language Models via Multi-Armed Bandit-based Context switching

Aditya Ramesh
Shivam Bhardwaj
Aditya Saibewar
Manohar Kaul

Content warning: This paper contains examples of harmful language and content. Recent advances in large language models (LLMs) have made them increasingly vulnerable to jailbreaking attempts, where malicious users manipulate models into generating harmful content. While existing approaches rely on either single-step attacks that trigger immediate safety responses or multi-step methods that inefficiently iterate prompts using other LLMs, we introduce ``Sequence of Context" (SoC) attacks that systematically alter conversational context through strategically crafted context-switching queries (CSQs). We formulate this as a multi-armed bandit (MAB) optimization problem, automatically learning optimal sequences of CSQs that gradually weaken the model's safety boundaries. Our theoretical analysis provides tight bounds on both the expected sequence length until successful jailbreak and the convergence of cumulative rewards. Empirically, our method achieves a 95\% attack success rate, surpassing PAIR by 63.15\%, AutoDAN by 60\%, and ReNeLLM by 50\%. We evaluate our attack across multiple open-source LLMs including Llama and Mistral variants. Our findings highlight critical vulnerabilities in current LLM safeguards and emphasize the need for defenses that consider sequential attack patterns rather than relying solely on static prompt filtering or iterative refinement.

Details

TMLR Journal 2024 Journal Article

Teacher-Guided Graph Contrastive Learning

Jay Nandy
Arnab Kumar Mondal
Manohar Kaul
Prathosh AP

State-of-the-art self-supervised representation learning methods for Graphs are typically based on contrastive learning (CL) principles. These CL objective functions can be posed as a supervised discriminative task using *'hard'* labels that consider any minor augmented pairs of graphs as 'equally positive'. However, such a notion of 'equal' pairs is incorrect for graphs as even a smaller 'discrete' perturbation may lead to large semantic changes that should be carefully encapsulated within the learned representations. This paper proposes a novel CL framework for GNNs, called *Teacher-guided Graph Contrastive Learning (TGCL)*, that incorporates 'soft' pseudo-labels to facilitate a more regularized discrimination. In particular, we propose a teacher-student framework where the student learns the representation by distilling the teacher's perception. Our TGCL framework can be adapted to existing CL methods to enhance their performance. Our empirical findings validate these claims on both inductive and transductive settings across diverse downstream tasks, including molecular graphs and social networks. Our experiments on benchmark datasets demonstrate that our framework consistently improves the average AUROC scores for molecules' property prediction and social network link prediction. Our code is available at: https://github.com/jayjaynandy/TGCL.

PDF Details

ICLR Conference 2020 Conference Paper

Few-Shot Learning on graphs via super-Classes based on Graph spectral Measures

Jatin Chauhan
Deepak Nathani
Manohar Kaul

We propose to study the problem of few-shot graph classification in graph neural networks (GNNs) to recognize unseen classes, given limited labeled graph examples. Despite several interesting GNN variants being proposed recently for node and graph classification tasks, when faced with scarce labeled examples in the few-shot setting, these GNNs exhibit significant loss in classification performance. Here, we present an approach where a probability measure is assigned to each graph based on the spectrum of the graph’s normalized Laplacian. This enables us to accordingly cluster the graph base-labels associated with each graph into super-classes, where the L^p Wasserstein distance serves as our underlying distance metric. Subsequently, a super-graph constructed based on the super-classes is then fed to our proposed GNN framework which exploits the latent inter-class relationships made explicit by the super-graph to achieve better class label separation among the graphs. We conduct exhaustive empirical evaluations of our proposed method and show that it outperforms both the adaptation of state-of-the-art graph classification methods to few-shot scenario and our naive baseline GNNs. Additionally, we also extend and study the behavior of our method to semi-supervised and active learning scenarios.

Details

NeurIPS Conference 2020 Conference Paper

Self-Supervised Few-Shot Learning on Point Clouds

Charu Sharma
Manohar Kaul

The increased availability of massive point clouds coupled with their utility in a wide variety of applications such as robotics, shape synthesis, and self-driving cars has attracted increased attention from both industry and academia. Recently, deep neural networks operating on labeled point clouds have shown promising results on supervised learning tasks like classification and segmentation. However, supervised learning leads to the cumbersome task of annotating the point clouds. To combat this problem, we propose two novel self-supervised pre-training tasks that encode a hierarchical partitioning of the point clouds using a cover-tree, where point cloud subsets lie within balls of varying radii at each level of the cover-tree. Furthermore, our self-supervised learning network is restricted to pre-train on the support set (comprising of scarce training examples) used to train the downstream network in a few-shot learning (FSL) setting. Finally, the fully-trained self-supervised network's point embeddings are input to the downstream task's network. We present a comprehensive empirical evaluation of our method on both downstream classification and segmentation tasks and show that supervised methods pre-trained with our self-supervised learning method significantly improve the accuracy of state-of-the-art methods. Additionally, our method also outperforms previous unsupervised methods in downstream classification tasks.

PDF Details

ICML Conference 2018 Conference Paper

Solving Partial Assignment Problems using Random Clique Complexes

Charu Sharma
Deepak Nathani
Manohar Kaul

We present an alternate formulation of the partial assignment problem as matching random clique complexes, that are higher-order analogues of random graphs, designed to provide a set of invariants that better detect higher-order structure. The proposed method creates random clique adjacency matrices for each k-skeleton of the random clique complexes and matches them, taking into account each point as the affine combination of its geometric neighborhood. We justify our solution theoretically, by analyzing the runtime and storage complexity of our algorithm along with the asymptotic behavior of the quadratic assignment problem (QAP) that is associated with the underlying random clique adjacency matrices. Experiments on both synthetic and real-world datasets, containing severe occlusions and distortions, provide insight into the accuracy, efficiency, and robustness of our approach. We outperform diverse matching algorithms by a significant margin.

Details