Search Results for author: Amin Saberi

Found 10 papers, 3 papers with code

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

no code implementations • 2 Oct 2024 • Mohammadreza Pourreza, Hailong Li, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, Sercan O. Arik

In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to improve candidate generation and selection.

Ranked #2 on Text-To-SQL on BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)

Large Language Model Text-To-SQL

Paper
Add Code

MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go Approximation

1 code implementation • 10 Jun 2024 • Alexandre Hayderi, Amin Saberi, Ellen Vitercik, Anders Wikum

Online Bayesian bipartite matching is a central problem in digital marketplaces and exchanges, including advertising, crowdsourcing, ridesharing, and kidney exchange.

Graph Neural Network

Paper
Code

CHESS: Contextual Harnessing for Efficient SQL Synthesis

1 code implementation • 27 May 2024 • Shayan Talaei, Mohammadreza Pourreza, Yu-Chen Chang, Azalia Mirhoseini, Amin Saberi

Translating natural language questions into SQL queries, known as text-to-SQL, is a long-standing research problem.

Ranked #11 on Text-To-SQL on BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)

Large Language Model Privacy Preserving +3

138

Paper
Code

Statistical Guarantees for Link Prediction using Graph Neural Networks

no code implementations • 5 Feb 2024 • Alan Chung, Amin Saberi, Morgane Austern

This paper derives statistical guarantees for the performance of Graph Neural Networks (GNNs) in link prediction tasks on graphs generated by a graphon.

Link Prediction

Paper
Add Code

A Local Graph Limits Perspective on Sampling-Based GNNs

no code implementations • 17 Oct 2023 • Yeganeh Alimohammadi, Luana Ruiz, Amin Saberi

We propose a theoretical framework for training Graph Neural Networks (GNNs) on large input graphs via training on small, fixed-size sampled subgraphs.

Node Classification

Paper
Add Code

Locality-Aware Graph-Rewiring in GNNs

no code implementations • 2 Oct 2023 • Federico Barbero, Ameya Velingker, Amin Saberi, Michael Bronstein, Francesco Di Giovanni

Graph Neural Networks (GNNs) are popular models for machine learning on graphs that typically follow the message-passing paradigm, whereby the feature of a node is updated recursively upon aggregating information over its neighbors.

Inductive Bias