Influence maximization (IM) refers to the problem of finding a subset of nodes in a network through which we could maximize our reach to other nodes in the network. This set is often called the "seed set", and its constituent nodes maximize the social diffusion process. IM has previously been studied in various settings, including under a time deadline, subject to constraints such as that of budget or coverage, and even subject to measures other than the centrality of nodes. The solution approach has generally been to prove that the objective function is submodular, or has a submodular proxy, and thus has a close greedy approximation. In this paper, we explore a variant of the IM problem where we wish to reach out to and maximize the probability of infection of a small subset of bounded capacity K. We show that this problem does not exhibit the same submodular guarantees as the original IM problem, for which we resort to the theory of gamma-weakly submodular functions. Subsequently, we develop a greedy algorithm that maximizes our objective despite the lack of submodularity. We also develop a suitable learning model that out-competes baselines on the task of predicting the top-K infected nodes, given a seed set as input.
@inproceedings{10.1145/3539597.3570433,abbr={WSDM},bibtex_show={true},author={Chakraborty, Pritish and Ranu, Sayan and Mantri, Krishna Sri Ipsit and De, Abir},title={Learning and Maximizing Influence in Social Networks Under Capacity Constraints},year={2023},isbn={9781450394079},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3539597.3570433},html={https://doi.org/10.1145/3539597.3570433},pdf={assets/pdf/wsdmfp0423-chakraborty1.pdf},doi={10.1145/3539597.3570433},booktitle={Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining},pages={733–741},numpages={9},keywords={gamma-weakly submodular functions, deep submodular functions, influence maximization, graph neural networks},location={Singapore, Singapore},series={WSDM '23}}
ICLR
STAGCN: Spatial-Temporal Attention Based Graph Convolutional Networks for COVID-19 Forecasting
Sasikumar, Nevasini, and Mantri, Krishna Sri Ipsit
In 2023 ICLR First Workshop on “Machine Learning & Global Health” 2023
@inproceedings{sasikumar2023stagcn,title={{STAGCN}: Spatial-Temporal Attention Based Graph Convolutional Networks for {COVID}-19 Forecasting},author={Sasikumar, Nevasini and Mantri, Krishna Sri Ipsit},booktitle={2023 ICLR First Workshop on {\textquotedblleft}Machine Learning {\&} Global Health{\textquotedblright}},year={2023},url={https://openreview.net/forum?id=k0E_VMXLXl},html={https://openreview.net/forum?id=k0E_VMXLXl},pdf={https://openreview.net/pdf?id=k0E_VMXLXl},abbr={ICLR},bibtex_show={true}}
ICLR
Attention Based Variational Graph Auto-Encoder (AVGAE)
Sasikumar, Nevasini, and Mantri, Krishna Sri Ipsit
@misc{sasikumar2023attention,title={Attention Based Variational Graph Auto-Encoder ({AVGAE})},author={Sasikumar, Nevasini and Mantri, Krishna Sri Ipsit},booktitle={ICLR 2023, Tiny Papers},year={2023},url={https://openreview.net/forum?id=j1gj0ndrk1},html={https://openreview.net/forum?id=j1gj0ndrk1},pdf={https://openreview.net/pdf?id=j1gj0ndrk1},abbr={ICLR},bibtex_show={true}}
MIDL
Synthetic Medical Image Generation Using Latent Diffusion Models and Large Language Models
Mantri, Krishna Sri Ipsit, and Sasikumar, Nevasini
In Medical Imaging with Deep Learning, short paper track 2023
@inproceedings{mantri2023synthetic,title={Synthetic Medical Image Generation Using Latent Diffusion Models and Large Language Models},author={Mantri, Krishna Sri Ipsit and Sasikumar, Nevasini},booktitle={Medical Imaging with Deep Learning, short paper track},year={2023},url={https://openreview.net/forum?id=EyVbjdbQZwt},abbr={MIDL},bibtex_show={true},pdf={https://openreview.net/pdf?id=EyVbjdbQZwt},html={https://openreview.net/forum?id=EyVbjdbQZwt}}