Workshop
Databases and AI (DBAI)
Nikolaos Vasiloglou · Parisa Kordjamshidi · Zenna Tavares · Maximilian Schleich · Nantia Makrynioti · Kirk Pruhs
Mon 13 Dec, 5:50 a.m. PST
Relational data represents the vast majority of data present in the enterprise world. Yet none of the ML computations happens inside a relational database where data reside. Instead a lot of time is wasted in denormalizing the data and moving them outside of the databases in order to train models. Relational learning, which takes advantage of relational data structure, has been a 20 year old research area, but it hasn’t been connected with relational database systems, despite the fact that relational databases are the natural space for storing relational data. Recent advances in database research have shown that it is possible to take advantage of the relational structure in data in order to accelerate ML algorithms. Research in relational algebra originating from the database community has shown that it is possible to further accelerate linear algebra operations. Probabilistic Programming has also been proposed as a framework for AI that can be realized in relational databases. Data programming, a mechanism for weak/self supervision is slowly migrating to the natural space of storing data, the database. At last, as models in deep learning grow, several systems are being developed for model management inside relational databases
Schedule
Mon 5:50 a.m. - 6:00 a.m.
|
Opening Remarks
(
Welcome from the organizers
)
>
SlidesLive Video |
🔗 |
Mon 6:00 a.m. - 6:45 a.m.
|
Machine Learning through Database Glasses
(
Invited Talk
)
>
SlidesLive Video |
Dan Olteanu 🔗 |
Mon 6:45 a.m. - 7:30 a.m.
|
Programmatic supervision for model centric AI
(
Invited talk
)
>
SlidesLive Video |
Paroma Varma 🔗 |
Mon 7:30 a.m. - 8:00 a.m.
|
Break
|
🔗 |
Mon 8:00 a.m. - 8:45 a.m.
|
The New DBfication of ML/AI
(
Invited Talk
)
>
SlidesLive Video |
Arun Kumar 🔗 |
Mon 8:45 a.m. - 9:08 a.m.
|
Collective Grounding: Relational Learning Meets Relational Theory
(
Invited Talk
)
>
SlidesLive Video |
Eriq Augustine 🔗 |
Mon 9:08 a.m. - 9:25 a.m.
|
Two Ways of Thinking about Weighted Relations
(
Invited Talk
)
>
SlidesLive Video |
David Chiang 🔗 |
Mon 9:25 a.m. - 10:20 a.m.
|
Lunch Break
|
🔗 |
Mon 10:20 a.m. - 10:34 a.m.
|
DRL-Clusters: Buffer Management with Clustering based Deep Reinforcement Learning
(
Contributed Talk
)
>
link
SlidesLive Video |
Kai Li · Qi Zhang · Lei Yu · Hong Min 🔗 |
Mon 10:34 a.m. - 10:48 a.m.
|
RASL: Relational Algebra in Scikit-Learn Pipelines
(
Contributed Talk
)
>
link
SlidesLive Video |
Chirag Sahni · Kiran Kate · Avi Shinnar · Thanh Lam Hoang · Martin Hirzel 🔗 |
Mon 10:48 a.m. - 11:02 a.m.
|
DP-KB: Data Programming with Knowledge Bases Improves Transformer Fine Tuning for Answer Sentence Selection
(
Contributed Talk
)
>
link
SlidesLive Video |
Nicolaas Jedema · Thuy Vu · Manish Gupta · Alessandro Moschitti 🔗 |
Mon 11:02 a.m. - 11:16 a.m.
|
Compressing (Multidimensional) Learned Bloom Filters
(
Contributed Talk
)
>
link
SlidesLive Video |
Angjela Davitkova · Damjan Gjurovski · Sebastian Michel 🔗 |
Mon 11:16 a.m. - 11:30 a.m.
|
Numerical Reasoning over Legal Contracts via Relational Database
(
Contributed Talk
)
>
link
SlidesLive Video |
Jiani Huang · Ziyang Li · Ilias Fountalis · Mayur Naik 🔗 |
Mon 11:30 a.m. - 12:00 p.m.
|
Deep Learning with Relations
(
Contributed Talk
)
>
link
SlidesLive Video |
Molham Aref 🔗 |
Mon 12:00 p.m. - 12:15 p.m.
|
Break
|
🔗 |
Mon 12:15 p.m. - 12:45 p.m.
|
Towards AI-Native Databases
(
Invited Talk
)
>
SlidesLive Video |
Olga Papaemmanouil 🔗 |
Mon 12:45 p.m. - 1:59 p.m.
|
AI workloads inside databases
(
Panel
)
>
SlidesLive Video |
Guy Van den Broeck · Alexander Ratner · Benjamin Moseley · Konstantinos Karanasos · Parisa Kordjamshidi · Molham Aref · Arun Kumar 🔗 |
Mon 2:00 p.m. - 2:05 p.m.
|
Closing Remarks
(
Closing Remarks
)
>
|
🔗 |
-
|
DP-KB: Data Programming with Knowledge Bases Improves Transformer Fine Tuning for Answer Sentence Selection ( Oral ) > link | Nicolaas Jedema · Thuy Vu · Thuy Vu · Manish Gupta · Alessandro Moschitti 🔗 |
-
|
RASL: Relational Algebra in Scikit-Learn Pipelines ( Oral ) > link | Kiran Kate · Avi Shinnar · Thanh Lam Hoang · Martin Hirzel 🔗 |
-
|
Compressing (Multidimensional) Learned Bloom Filters ( Oral ) > link | Angjela Davitkova · Damjan Gjurovski · Sebastian Michel 🔗 |
-
|
DRL-Clusters: Buffer Management with Clustering based Deep Reinforcement Learning ( Oral ) > link | Kai Li · Qi Zhang · Lei Yu · Hong Min 🔗 |
-
|
Numerical Reasoning over Legal Contracts via Relational Database ( Oral ) > link | Jiani Huang · Ziyang Li · Ilias Fountalis · Mayur Naik 🔗 |