4 citations · 9 across the 10 of their papers we have counts for
10 papers
Position: Avoid Overstretching LLMs for every Enterprise Task
Kuldeep Singh, Anson Bastos, Isaiah Onando Mulang'
Enterprise workloads are dominated by deterministic, structured, and knowledge-dependent tasks operating under strict cost, latency, and reliability constraints. While these are of…
Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs
Anson Bastos, Kuldeep Singh, Abhishek Nadgeri +2
We present the Evolving Graph Fourier Transform (EFT), the first invertible spectral transform that captures evolving representations on temporal graphs. We motivate our work by th…
Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?
Anson Bastos, Kuldeep Singh, Abhishek Nadgeri +3
In this paper we present a novel method, (), for faster evaluation of Knowledge Graph (KG) completion approaches. Current ranking-bas…
Learnable Spectral Wavelets on Dynamic Graphs to Capture Global Interactions
Anson Bastos, Abhishek Nadgeri, Kuldeep Singh +2
Learning on evolving(dynamic) graphs has caught the attention of researchers as static methods exhibit limited performance in this setting. The existing methods for dynamic graphs…
How Expressive are Transformers in Spectral Domain for Graphs?
Anson Bastos, Abhishek Nadgeri, Kuldeep Singh +3
The recent works proposing transformer-based models for graphs have proven the inadequacy of Vanilla Transformer for graph representation learning. To understand this inadequacy, t…
ALLWAS: Active Learning on Language models in WASserstein space
Anson Bastos, Manohar Kaul
Active learning has emerged as a standard paradigm in areas with scarcity of labeled training data, such as in the medical domain. Language models have emerged as the prevalent cho…
HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations
Anson Bastos, Kuldeep Singh, Abhishek Nadgeri +3
Recently, several Knowledge Graph Embedding (KGE) approaches have been devised to represent entities and relations in dense vector space and employed in downstream tasks such as li…
KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction
Abhishek Nadgeri, Anson Bastos, Kuldeep Singh +4
We present a novel method for relation extraction (RE) from a single sentence, mapping the sentence and two given entities to a canonical fact in a knowledge graph (KG). Especially…
RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural Network
Anson Bastos, Abhishek Nadgeri, Kuldeep Singh +4
In this paper, we present a novel method named RECON, that automatically identifies relations in a sentence (sentential relation extraction) and aligns to a knowledge graph (KG). R…
Learning sentence embeddings using Recursive Networks
Anson Bastos
Learning sentence vectors that generalise well is a challenging task. In this paper we compare three methods of learning phrase embeddings: 1) Using LSTMs, 2) using recursive nets,…