Ishika Agarwal

Ishika Agarwal

Will code for dark chocolate

Projects

[Master’s Thesis] Active Graph Anomaly Detection

Ishika Agarwal, Hanghang Tong

Recently, detecting anomalies in attributed networks has gained a lot of attention from research communities due to the numerous real-world use cases in the financial, social media, medical, and agricultural domains. This thesis aims to explore node anomaly detection in two different aspects: soft-labeling, and multi-armed bandits. The environment in both settings is constrained to an active learning scenario where there is no direct access to ground truth labels but access to an oracle. This thesis comprises of three works: one using soft-labeling, another with multi-armed bandits, and a third that explores a combination of both. We present experimental results for each work to justify the algorithmic decisions that were made. Future work is also discussed to build on top of these methods.

Download here

Generative Transformers for Diverse text Generation

Ishika Agarwal, Priyanka Kargupta, Bowen Jin, Akul Joshi

Diverse text generation is an important and challenging task. Existing methods mainly adopt a discriminative model, with the underlying assumption that the input text-to-output text projection is a one-one mapping. However, this is not true in the real world, since given one single input text, there can be multiple ground truth output text candidates. For example, in the commonsense generation, given a list of knowledge entities, there should be more than one way to use them to come up with a sentence. This motivates us to capture the underlying text semantics distribution with generative models (e.g., VAE and diffusion models). On the other hand, Transformer architecture has been demonstrated to be effective in text semantics capturing. Then the problem comes to how to effectively combine the Transformer architecture with the generative models. Our project aims to combine the best of both worlds by introducing VAE & Diffusion model into transformers. Specifically, we want to apply them to two downstream tasks: common sense generation and question generation. We include results, and some future work to further this project.

Download here