145 citations · 365 across the 24 of their papers we have counts for
24 papers
CT: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees
S M Rafiuddin, Atriya Sen
Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a branching reply tree. We study…
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
FoodSense: A Multisensory Food Dataset and Benchmark for Predicting Taste, Smell, Texture, and Sound from Images
Sabab Ishraq, Aarushi Aarushi, Juncai Jiang +1
Humans routinely infer taste, smell, texture, and even sound from food images a phenomenon well studied in cognitive science. However, prior vision language research on food has fo…
Gemma 3 Technical Report
Gemma Team, Aishwarya Kamath, Johan Ferret +209
We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision underst…
Gemma 2: Improving Open Language Models at a Practical Size
Gemma Team, Morgane Riviere, Shreya Pathak +195
In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In th…
Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
Zhikai Chen, Haitao Mao, Jingzhe Liu +8
Given the ubiquity of graph data and its applications in diverse domains, building a Graph Foundation Model (GFM) that can work well across different graphs and tasks with a unifie…
Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning
Bahare Fatemi, Mehran Kazemi, Anton Tsitsulin +6
Large language models (LLMs) have showcased remarkable reasoning capabilities, yet they remain susceptible to errors, particularly in temporal reasoning tasks involving complex tem…
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…
Don't Forget to Connect! Improving RAG with Graph-based Reranking
Jialin Dong, Bahare Fatemi, Bryan Perozzi +2
Retrieval Augmented Generation (RAG) has greatly improved the performance of Large Language Model (LLM) responses by grounding generation with context from existing documents. Thes…
Let Your Graph Do the Talking: Encoding Structured Data for LLMs
Bryan Perozzi, Bahare Fatemi, Dustin Zelle +4
How can we best encode structured data into sequential form for use in large language models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly represent…
The Graph Lottery Ticket Hypothesis: Finding Sparse, Informative Graph Structure
Anton Tsitsulin, Bryan Perozzi
Graph learning methods help utilize implicit relationships among data items, thereby reducing training label requirements and improving task performance. However, determining the o…
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…
HUGE: Huge Unsupervised Graph Embeddings with TPUs
Brandon Mayer, Anton Tsitsulin, Hendrik Fichtenberger +2
Graphs are a representation of structured data that captures the relationships between sets of objects. With the ubiquity of available network data, there is increasing industrial…
Examining the Effects of Degree Distribution and Homophily in Graph Learning Models
Mustafa Yasir, John Palowitch, Anton Tsitsulin +2
Despite a surge in interest in GNN development, homogeneity in benchmarking datasets still presents a fundamental issue to GNN research. GraphWorld is a recent solution which uses…
Unsupervised Embedding Quality Evaluation
Anton Tsitsulin, Marina Munkhoeva, Bryan Perozzi
Unsupervised learning has recently significantly gained in popularity, especially with deep learning-based approaches. Despite numerous successes and approaching supervised-level p…
On Classification Thresholds for Graph Attention with Edge Features
Kimon Fountoulakis, Dake He, Silvio Lattanzi +3
The recent years we have seen the rise of graph neural networks for prediction tasks on graphs. One of the dominant architectures is graph attention due to its ability to make pred…
Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank
Alessandro Epasto, Vahab Mirrokni, Bryan Perozzi +2
Personalized PageRank (PPR) is a fundamental tool in unsupervised learning of graph representations such as node ranking, labeling, and graph embedding. However, while data privacy…
TF-GNN: Graph Neural Networks in TensorFlow
Oleksandr Ferludin, Arno Eigenwillig, Martin Blais +24
TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow. It is designed from the bottom up to support the kinds of rich heterogeneous graph data that…
Tackling Provably Hard Representative Selection via Graph Neural Networks
Mehran Kazemi, Anton Tsitsulin, Hossein Esfandiari +4
Representative Selection (RS) is the problem of finding a small subset of exemplars from a dataset that is representative of the dataset. In this paper, we study RS for attributed…
Synthetic Graph Generation to Benchmark Graph Learning
Anton Tsitsulin, Benedek Rozemberczki, John Palowitch +1
Graph learning algorithms have attained state-of-the-art performance on many graph analysis tasks such as node classification, link prediction, and clustering. It has, however, bec…
GraphWorld: Fake Graphs Bring Real Insights for GNNs
John Palowitch, Anton Tsitsulin, Brandon Mayer +1
Despite advances in the field of Graph Neural Networks (GNNs), only a small number (~5) of datasets are currently used to evaluate new models. This continued reliance on a handful…
InstantEmbedding: Efficient Local Node Representations
Ştefan Postăvaru, Anton Tsitsulin, Filipe Miguel Gonçalves de Almeida +3
In this paper, we introduce InstantEmbedding, an efficient method for generating single-node representations using local PageRank computations. We theoretically prove that our appr…
Graph Clustering with Graph Neural Networks
Anton Tsitsulin, John Palowitch, Bryan Perozzi +1
Graph Neural Networks (GNNs) have achieved state-of-the-art results on many graph analysis tasks such as node classification and link prediction. However, important unsupervised pr…
Just SLaQ When You Approximate: Accurate Spectral Distances for Web-Scale Graphs
Anton Tsitsulin, Marina Munkhoeva, Bryan Perozzi
Graph comparison is a fundamental operation in data mining and information retrieval. Due to the combinatorial nature of graphs, it is hard to balance the expressiveness of the sim…