393 citations · 634 across the 19 of their papers we have counts for
20 papers
Transformers Struggle to Learn to Search
Abulhair Saparov, Srushti Pawar, Shreyas Pimpalgaonkar +6
Search is an ability foundational in many important tasks, and recent studies have shown that large language models (LLMs) struggle to perform search robustly. It is unknown whethe…
Understanding Transformer Reasoning Capabilities via Graph Algorithms
Clayton Sanford, Bahare Fatemi, Ethan Hall +5
Which transformer scaling regimes are able to perfectly solve different classes of algorithmic problems? While tremendous empirical advances have been attained by transformer-based…
UGSL: A Unified Framework for Benchmarking Graph Structure Learning
Bahare Fatemi, Sami Abu-El-Haija, Anton Tsitsulin +5
Graph neural networks (GNNs) demonstrate outstanding performance in a broad range of applications. While the majority of GNN applications assume that a graph structure is given, so…
Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples
Abulhair Saparov, Richard Yuanzhe Pang, Vishakh Padmakumar +4
Given the intractably large size of the space of proofs, any model that is capable of general deductive reasoning must generalize to proofs of greater complexity. Recent studies ha…
TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs
Aditya Sharma, Apoorv Saxena, Chitrank Gupta +3
Recent years have witnessed much interest in temporal reasoning over knowledge graphs (KG) for complex question answering (QA), but there remains a substantial gap in human capabil…
Stay Positive: Knowledge Graph Embedding Without Negative Sampling
Ainaz Hajimoradlou, Mehran Kazemi
Knowledge graphs (KGs) are typically incomplete and we often wish to infer new facts given the existing ones. This can be thought of as a binary classification problem; we aim to p…
SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
Bahare Fatemi, Layla El Asri, Seyed Mehran Kazemi
Graph neural networks (GNNs) work well when the graph structure is provided. However, this structure may not always be available in real-world applications. One solution to this pr…
Out-of-Sample Representation Learning for Multi-Relational Graphs
Marjan Albooyeh, Rishab Goel, Seyed Mehran Kazemi
Many important problems can be formulated as reasoning in knowledge graphs. Representation learning has proved extremely effective for transductive reasoning, in which one needs to…
Time2Vec: Learning a Vector Representation of Time
Seyed Mehran Kazemi, Rishab Goel, Sepehr Eghbali +7
Time is an important feature in many applications involving events that occur synchronously and/or asynchronously. To effectively consume time information, recent studies have focu…
Diachronic Embedding for Temporal Knowledge Graph Completion
Rishab Goel, Seyed Mehran Kazemi, Marcus Brubaker +1
Knowledge graphs (KGs) typically contain temporal facts indicating relationships among entities at different times. Due to their incompleteness, several approaches have been propos…
Representation Learning for Dynamic Graphs: A Survey
Seyed Mehran Kazemi, Rishab Goel, Kshitij Jain +4
Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learni…
Structure Learning for Relational Logistic Regression: An Ensemble Approach
Nandini Ramanan, Gautam Kunapuli, Tushar Khot +5
We consider the problem of learning Relational Logistic Regression (RLR). Unlike standard logistic regression, the features of RLRs are first-order formulae with associated weight…
Record Linkage to Match Customer Names: A Probabilistic Approach
Bahare Fatemi, Seyed Mehran Kazemi, David Poole
Consider the following problem: given a database of records indexed by names (e.g., name of companies, restaurants, businesses, or universities) and a new name, determine whether t…
SimplE Embedding for Link Prediction in Knowledge Graphs
Seyed Mehran Kazemi, David Poole
Knowledge graphs contain knowledge about the world and provide a structured representation of this knowledge. Current knowledge graphs contain only a small subset of what is true i…
RelNN: A Deep Neural Model for Relational Learning
Seyed Mehran Kazemi, David Poole
Statistical relational AI (StarAI) aims at reasoning and learning in noisy domains described in terms of objects and relationships by combining probability with first-order logic.…
Domain Recursion for Lifted Inference with Existential Quantifiers
Seyed Mehran Kazemi, Angelika Kimmig, Guy Van den Broeck +1
In recent work, we proved that the domain recursion inference rule makes domain-lifted inference possible on several relational probability models (RPMs) for which the best known t…
Comparing Aggregators for Relational Probabilistic Models
Seyed Mehran Kazemi, Bahare Fatemi, Alexandra Kim +5
Relational probabilistic models have the challenge of aggregation, where one variable depends on a population of other variables. Consider the problem of predicting gender from mov…
New Liftable Classes for First-Order Probabilistic Inference
Seyed Mehran Kazemi, Angelika Kimmig, Guy Van den Broeck +1
Statistical relational models provide compact encodings of probabilistic dependencies in relational domains, but result in highly intractable graphical models. The goal of lifted i…
A Learning Algorithm for Relational Logistic Regression: Preliminary Results
Bahare Fatemi, Seyed Mehran Kazemi, David Poole
Relational logistic regression (RLR) is a representation of conditional probability in terms of weighted formulae for modelling multi-relational data. In this paper, we develop a l…
Why is Compiling Lifted Inference into a Low-Level Language so Effective?
Seyed Mehran Kazemi, David Poole
First-order knowledge compilation techniques have proven efficient for lifted inference. They compile a relational probability model into a target circuit on which many inference q…