Welcome to CODS-COMAD 2024

CODS-COMAD is a premier international conference focusing on scientific work in Databases, Data Sciences and their applications. Being held for the 7th time as a common conference bringing together the COMAD and the CODS communities, this conference invites researchers in the field of databases, data sciences and their applications to submit their original work.

The conference has a long and rich history. COMAD, primarily a data management conference, started in 1989. CODS started in 2014 with AI, Machine Learning and Data Science as its focus.These merged in 2018 to become the vibrant CODS-COMAD conference of today. The current conference is marked by keynote talks by stalwarts, research and applied data science tracks presenting original work of high quality, topical tutorials and demo tracks showcasing innovation in action. The Young Researchers Symposium has evolved as a valued forum for providing early feedback to budding and early career researchers. The conference consistently attracts funding from top research labs, and other data-centric companies and startups. This sponsorship enables providing support to students from across the country to attend the conference. Since 2021, the conference has been hosting a track on Diversity and Inclusion to promote this crucial aspect in the data science and databases community. In short, the conference has been striving to bring the data-centric community together, specially in India, and also more generally around the world.

CODS-COMAD 2024 will be hosted by IIIT Bangalore.


================= Research Track and Applied Data Science Track =================

CODS-COMAD 2024 will accept research papers in two tracks: 1. Regular Research Track, and 2. Applied Data Sciences (ADS) Track. The latter is a new addition since 2021. Authors are invited to submit their research papers to one of these two tracks.

The Research Track solicits submissions that present original and innovative research challenges and solutions. Papers can range from theoretical contributions to systems and algorithms to experimental research. The Applied Data Science (ADS) Track is distinct from the Research Track in that submissions should focus on applied challenges addressing real-world problems and / or systems demonstrating tangible impact/value in their respective domains. The ADS Track submissions should highlight the target user needs and potential users.

For example, a research track paper may address some novel challenges around question-answering that may apply across many domains, languages, etc. An ADS Track paper may have a focus on a corpus from the bio-chemical domain, and may address problems that are specific to that domain. The target users may be bio-chemical engineers and researchers. As another example, a deployment of an app or website that helps farmers keep track of market prices of various products would be suitable for the ADS track, and farmers or agricultural traders may benefit from the solutions.

It is the authors’ responsibility to submit their paper into the appropriate track. Papers that do not satisfy the requirements of the track may be rejected without a review. For example, a paper that does not address a novel research problem or make generalizable contributions may not be suitable for the research track. On the other hand, a paper that does not target a specific real world user case and group of users may be rejected without review from the ADS Track. It is strongly recommended that authors read the Call for Papers for both tracks carefully before choosing a track.


================= Research Track =================

We invite the submission of papers describing innovative and original research contributions in the areas of data science, data management, data mining, machine learning, and artificial intelligence. Papers can range from theoretical contributions to systems and algorithms to experimental research and benchmarking. The research track invites two type of submissions:

Full papers: 8 pages + (unlimited) references.
Short papers: 4 pages + (unlimited) references.

The goal of the short papers is to provide a venue for innovative ideas such as engineered solutions, exciting work-in-progress or even negative results that would be interesting to the broader community. The review process will take place in two stages.

1. In the first stage of the review, papers will be grouped as Accept, Major Revision or Reject.
2. In the second stage of the review, authors can revise and resubmit Major Revision papers. They will then be regrouped as Accept or Reject.

Authors of accepted full papers must present their work as both a talk and a poster at the conference; accepted short papers must present their work as a poster. All accepted papers will appear in the proceedings of the conference, which will be published in the ACM Digital Library (Approval pending).
Topics of Interest include, but are not limited to, the following:

* AI, ML, and Data Mining: Classification and regression; Knowledge discovery; knowledge representation and knowledge-based systems; data preprocessing and wrangling; feature engineering; reinforcement learning; deep learning; Bayesian methods; time series analysis; optimization; graphical models; statistical relational learning; matrix and tensor methods; parallel and distributed learning; semi- and unsupervised learning; graph mining; network analytics; text analytics and NLP; information retrieval; learning-based computer vision; multimodal learning and analytics; human-in-the-loop learning; planning and reasoning; ML for mobiles and other resource-constrained environments; federated learning; AutoML; causality; fairness, accountability, transparency, and explainability in AI/ML; weak supervision and data augmentation; new benchmark tasks and datasets for AI/ML/data mining.

* Data Science-based Computing: Social network analysis; social computing; recommender systems; computational advertising; bioinformatics; computational neuroscience; multimedia processing; crowdsourcing; robotics and autonomous systems; analytics on sensor networks and IoT; surveillance/monitoring and anomaly detection in networked systems; urban computing; technology for emerging markets.

* Data Management: Data models and query languages; query processing and optimisation; indexing and storage systems; key-value and NoSQL stores; transaction processing; blockchains; distributed and cloud data systems; big data and dataflow systems; data warehousing and OLAP; spatio-temporal and graph data management; scientific and multimedia databases; data management for ML/AI workloads; ML/AI methods for data management; data cleaning and integration; data provenance; data streams; uncertain and probabilistic databases; data crowdsourcing; database usability and query interfaces; data visualisation and visual analytics; data management on modern hardware; data privacy, security, and ethics; performance tuning and benchmarking; new benchmark tasks and datasets for data management.

Sharing and Reproducibility

To enable reproducibility and data reuse, authors are encouraged to share artifacts including software, algorithms, protocols, code, datasets and other useful materials related to the research.

Additionally, please see this page to help you decide between the Research Track and Applied Data Science Track.

Please read the Dual submission, Plagiarism, and Conflict of Interest policies before finalising your submission.

Several technical awards are available for best paper, etc. Please see the Awards page for details.

Partial travel Grants will be available for students (both domestic and international) whose papers are accepted. Presenters will also have the option to present the papers virtually.
Double Anonymity Requirement

CODS-COMAD 2024 will be using double-anonymous reviewing for Research Track papers (but not the ADS Track papers). Since this is the first time this requirement is being added, please review the instructions below carefully.

Authors’ names and affiliations must not appear on the title page or anywhere else in the submission. Funding sources must not be acknowledged anywhere in the submission. Research group members, or other colleagues or collaborators, must not be acknowledged anywhere in the submission. Only after acceptance at the camera ready stage should the author list, acknowledgments, and funding sources be added to the paper.

The file names of any documents submitted must not identify the authors of the submission. Source file naming must also be done with care, to avoid identifying the authors’ names in the submission’s associated metadata.

To avoid compromising the double-anonymity requirement, we request that the authors refrain from publicizing and uploading versions of their submitted manuscripts to pre-publication servers, such as arXiv, and other online forums during the reviewing period. If a version of a submission already resides on a pre-publication server, such as arXiv, the authors do not need to remove it before submitting to CODS-COMAD.

Be careful when referring to related past work, particularly your own, in the paper. Authors must refer to their own past work in the third person. This allows setting the context for your submission, while at the same time preserving anonymity. Do not omit referring to your own past related work because that could reveal your identity by negation. Limit self-references to only the essential ones. Extended versions of the submitted paper (e.g., technical reports or URLs for downloadable versions) must not be referenced. Many ACM conferences have successfully followed double anonymity for decades to offer more equity for all authors in the reviewing process. Common sense and careful writing can go a long way toward preserving double anonymity without diminishing the quality or impact of a paper. It is the responsibility of the authors to do their very best to preserve double anonymity.

Papers that do not follow the guidelines here, or otherwise potentially reveal the identity of the authors, are subject to Desk Rejection. No exceptions will be made for Research Track papers. If the authors of a submission feel that double anonymity needs to be violated, for example to reveal the identity of a publicly deployed system, they may consider submitting their work to the ADS Track that does not impose this double anonymity requirement.
Important dates

All deadlines are Anywhere on Earth (AoE, UTC-1200)

July 10, 2023: Abstract submission
July 17, 2023: Submission of papers
September 11, 2023: First stage decision notifications (Accept/Reject/Revision)
October 11, 2023: Submission of revised papers
November 3, 2023: Final decision notifications (Accept/Reject)
November 30, 2023: Camera ready due


================= Applied Data Sciences Track =================

The Applied Data Sciences (ADS) track invites both full (8 pages + unlimited references) as well as short (4 pages + unlimited references) papers describing the design, implementation and results of solutions and systems for application of data science techniques to real-world problems.

The review process will take place in two stages.

1. In the first stage of the review, papers will be grouped as Accept, Major Revision or Reject.
2. In the second stage of the review, authors can revise and resubmit Major Revision papers. They will then be regrouped as Accept or Reject.

Accepted papers will be given the opportunity to present their work as an oral presentation. Accepted papers will appear in the proceedings of the conference, which will be published in ACM Digital Library (Approval pending).

Topics of interest include, but are not limited to the following:

* Novel combination of data science applications in domains such as education, software engineering, cloud computing, agriculture, transportation, energy, real estate, manufacturing, finance, retail, healthcare, e-commerce, digital marketing, telecommunications, social media and computational advertising, public policy, bio-chemical engineering, pollution tracking and climate change, material science, AI for natural sciences, bioinformatics, etc.

* Deployed experience papers from industry, government agencies, startups and NGOs relating to the large-scale deployment of data science applications. Of particular interest are papers addressing issues relating to infrastructure for scale, ease of adoption, and new data science/management technologies. Papers should highlight pain points and new challenges emerging due to deployment of these new technologies. Verifiable evidence of business impact, social impact or other real-world impact from such deployments are encouraged.

* Data sets: Applied scientific work on handling large or complex data sets from specific domains (e.g., noisy/incomplete medical data, judicial records, etc.).

* Ethical issues in data science applications, fairness and bias, trust, data privacy, explainability, etc., especially when these issues are considered in relation to deployed systems.

Sharing and Reproducibility

Authors are strongly encouraged to make their code and data publicly accessible during the review process, unless there is an inevitable reason that prohibits sharing (e.g., it requires data from a specific company or it is medical data where there is no public alternative). Algorithms and resources used in a paper should be described as completely as possible to enable reproducibility. This includes model parameters, experimental methodology, hardware and software platforms used during empirical evaluations, and results. The reproducibility factor will play an important role in the assessment of each submission. In the case where data cannot be released publicly, authors are encouraged to include experiments on relevant public datasets and/or create simulated data with the same properties.

Additionally, please see this page to help you decide between the Research Track and Applied Data Science Track.

Please read the Dual submission, Plagiarism and Conflict of Interest policies before finalising your submission.

Several technical awards are available for best paper, etc. Please see the Awards page for details.

Partial travel Grants will be available for students (both domestic and international) whose papers are accepted. Note that each paper must be presented in-person.
Important dates

All deadlines are Anywhere on Earth (AoE, UTC-1200)

July 10, 2023: Abstract submission
July 17, 2023: Submission of papers
September 11, 2023: First Stage Accept/Major Revision/ Reject decisions.
October 11, 2023: Re-submission of revised papers
November 3, 2023: Final notification of Accept/Reject decisions
November 30, 2023: Camera ready due