Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning
Sahil Mishra, Srinitish Srinivasan, Sourish Dasgupta +1
Real-world knowledge is often organized as hierarchies such as product taxonomies, medical ontologies, and label trees, yet learning hierarchical representations is challenging due…
cs.LG2025
Can we ease the Injectivity Bottleneck on Lorentzian Manifolds for Graph Neural Networks?
Srinitish Srinivasan, Omkumar CU
While hyperbolic GNNs show promise for hierarchical data, they often have limited discriminative power compared to Euclidean counterparts or the WL test, due to non-injective aggre…
cs.LG2025
Predict, Cluster, Refine: A Joint Embedding Predictive Self-Supervised Framework for Graph Representation Learning
Srinitish Srinivasan, Omkumar CU
Graph representation learning has emerged as a cornerstone for tasks like node classification and link prediction, yet prevailing self-supervised learning (SSL) methods face challe…