Zafaryab Rasool

Zafaryab Rasool

Auto-generated profile, based on publicly available information

Zafaryab Rasool

Applied Artificial Intelligence Institute, Deakin University, Geelong, Victoria, Australia

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 June 2024 in Natural Language Processing Journal
Verified
Journal Article
Open access
ZRZafaryab Rasool
Zafaryab Rasool
SKStefanus Kurniawan
Stefanus Kurniawan
SBSherwin Balugo
Sherwin Balugo
SBScott Barnett
Scott Barnett
RVRajesh Vasa
Rajesh Vasa
ABAlex Bahar-Fuchs
Alex Bahar-Fuchs

30 December 2022 in Pattern Recognition
Verified
Journal Article
Closed access
ZRZafaryab Rasool
Zafaryab Rasool
SASunil Aryal
Sunil Aryal
MBMohamed Reda Bouadjenek
Mohamed Reda Bouadjenek
RDRichard Dazeley
Richard Dazeley

23 June 2020 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
ZRZafaryab Rasool
Zafaryab Rasool
RZRui Zhou
Rui Zhou
LCLu Chen
Lu Chen
CLChengfei Liu
Chengfei Liu
JXJiajie Xu
Jiajie Xu
Density Peaks Clustering (DPC), a novel density-based clustering approach, has received considerable attention of the research community primarily due to its simplicity and less parameter requirement. However, the clusters obtained using DPC are influenced by its sensitive parameter $d_c$ depending on data distribution and requirements of users. Besides, the original DPC algorithm requires visiting a large number of objects, making it slow. To this end, this paper investigates index-based solutions for DPC. Specifically, we propose two list-based indices: (i) a simple List Index and (ii) an advanced Cumulative Histogram Index. Efficient query algorithms are proposed for these indices which significantly avoids irrelevant comparisons at the cost of space. To remedy this for memory-constrained systems, we further introduce an approximate solution to the above indices allowing substantial reduction in the space cost, provided slight inaccuracies are admissible. Furthermore, owing to considerably lower memory requirements of existing tree-based index structures, we also present effective pruning techniques and efficient query algorithms to support DPC using Quadtree and R-tree indices. Finally, we evaluate all the above indices and present the findings and results, obtained from extensive experiments on six datasets. The experimental insights obtained help to guide in selecting the befitting index.

14 April 2024
Verified
Conference Paper
Open access
ZRZafaryab Rasool
Zafaryab Rasool
SBScott Barnett
Scott Barnett
DWDavid Willie
David Willie
SKStefanus Kurniawan
Stefanus Kurniawan
SBSherwin Balugo
Sherwin Balugo
MAMohamed Almorsy Abdelrazek
Mohamed Almorsy Abdelrazek
Large language models (LLMs) enable state-of-the-art semantic capabilities to be added to software systems such as semantic search of unstructured documents and text generation. However, these models are computationally expensive. At scale, the cost of serving thousands of users increases massively affecting also user experience. To address this problem, semantic caches are used to check for answers to similar queries (that may have been phrased differently) without hitting the LLM service. Due to the nature of these semantic cache techniques that rely on query embeddings, there is a high chance of errors impacting user confidence in the system. Adopting semantic cache techniques usually requires testing the effectiveness of a semantic cache (accurate cache hits and misses) which requires a labelled test set of similar queries and responses which is often unavailable. In this paper, we present VaryGen, an approach for using LLMs for test input generation that produces similar questions from unstructured text documents. Our novel approach uses the reasoning capabilities of LLMs to 1) adapt queries to the domain, 2) synthesise subtle variations to queries, and 3) evaluate the synthesised test dataset. We evaluated our approach in the domain of a student question and answer system by qualitatively analysing 100 generated queries and result pairs, and conducting an empirical case study with an open source semantic cache. Our results show that query pairs satisfy human expectations of similarity and our generated data demonstrates failure cases of a semantic cache. Additionally, we also evaluate our approach on Qasper dataset. This work is an important first step into test input generation for semantic applications and presents considerations for practitioners when calibrating a semantic cache.

23 July 2020 in arXiv
Verified
Preprint
Open access
PDF file
ZRZafaryab Rasool
Zafaryab Rasool
RZRui Zhou
Rui Zhou
LCLu Chen
Lu Chen
CLChengfei Liu
Chengfei Liu
JXJiajie Xu
Jiajie Xu
Density Peak Clustering (DPC), a popular density-based clustering approach, has received considerable attention from the research community primarily due to its simplicity and fewer-parameter requirement. However, the resultant clusters obtained using DPC are influenced by the sensitive parameter $d_c$, which depends on data distribution and requirements of different users. Besides, the original DPC algorithm requires visiting a large number of objects, making it slow. To this end, this paper investigates index-based solutions for DPC. Specifically, we propose two list-based index methods viz. (i) a simple List Index, and (ii) an advanced Cumulative Histogram Index. Efficient query algorithms are proposed for these indices which significantly avoids irrelevant comparisons at the cost of space. For memory-constrained systems, we further introduce an approximate solution to the above indices which allows substantial reduction in the space cost, provided that slight inaccuracies are admissible. Furthermore, owing to considerably lower memory requirements of existing tree-based index structures, we also present effective pruning techniques and efficient query algorithms to support DPC using the popular Quadtree Index and R-tree Index. Finally, we practically evaluate all the above indices and present the findings and results, obtained from a set of extensive experiments on six synthetic and real datasets. The experimental insights obtained can help to guide in selecting a befitting index.