Search Results for author: Neil Shah

Found 52 papers, 31 papers with code

Improving Out-of-Vocabulary Handling in Recommendation Systems

no code implementations27 Mar 2024 William Shiao, Mingxuan Ju, Zhichun Guo, Xin Chen, Evangelos Papalexakis, Tong Zhao, Neil Shah, Yozen Liu

This work focuses on a complementary problem: recommending new users and items unseen (out-of-vocabulary, or OOV) at training time.

Recommendation Systems

How Does Message Passing Improve Collaborative Filtering?

no code implementations27 Mar 2024 Mingxuan Ju, William Shiao, Zhichun Guo, Yanfang Ye, Yozen Liu, Neil Shah, Tong Zhao

A branch of research enhances CF methods by message passing used in graph neural networks, due to its strong capabilities of extracting knowledge from graph-structured data, like user-item bipartite graphs that naturally exist in CF.

Collaborative Filtering Recommendation Systems +1

Node Duplication Improves Cold-start Link Prediction

no code implementations15 Feb 2024 Zhichun Guo, Tong Zhao, Yozen Liu, Kaiwen Dong, William Shiao, Neil Shah, Nitesh V. Chawla

Graph Neural Networks (GNNs) are prominent in graph machine learning and have shown state-of-the-art performance in Link Prediction (LP) tasks.

Link Prediction Recommendation Systems

LLaGA: Large Language and Graph Assistant

2 code implementations13 Feb 2024 Runjin Chen, Tong Zhao, Ajay Jaiswal, Neil Shah, Zhangyang Wang

Graph Neural Networks (GNNs) have empowered the advance in graph-structured data analysis.

Position: Graph Foundation Models are Already Here

1 code implementation3 Feb 2024 Haitao Mao, Zhikai Chen, Wenzhuo Tang, Jianan Zhao, Yao Ma, Tong Zhao, Neil Shah, Mikhail Galkin, Jiliang Tang

Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains.


Neural Scaling Laws on Graphs

1 code implementation3 Feb 2024 Jingzhe Liu, Haitao Mao, Zhikai Chen, Tong Zhao, Neil Shah, Jiliang Tang

In this work, we delve into neural scaling laws on graphs from both model and data perspectives.

Graph Classification Link Prediction +1

Graph Transformers for Large Graphs

1 code implementation18 Dec 2023 Vijay Prakash Dwivedi, Yozen Liu, Anh Tuan Luu, Xavier Bresson, Neil Shah, Tong Zhao

As such, a key innovation of this work lies in the creation of a fast neighborhood sampling technique coupled with a local attention mechanism that encompasses a 4-hop reception field, but achieved through just 2-hop operations.

Graph Learning Graph Property Prediction +3

A Topological Perspective on Demystifying GNN-Based Link Prediction Performance

1 code implementation6 Oct 2023 Yu Wang, Tong Zhao, Yuying Zhao, Yunchao Liu, Xueqi Cheng, Neil Shah, Tyler Derr

Despite the widespread belief that low-degree nodes exhibit poorer LP performance, our empirical findings provide nuances to this viewpoint and prompt us to propose a better metric, Topological Concentration (TC), based on the intersection of the local subgraph of each node with the ones of its neighbors.

Link Prediction

Revisiting Link Prediction: A Data Perspective

1 code implementation1 Oct 2023 Haitao Mao, Juanhui Li, Harry Shomer, Bingheng Li, Wenqi Fan, Yao Ma, Tong Zhao, Neil Shah, Jiliang Tang

We recognize three fundamental factors critical to link prediction: local structural proximity, global structural proximity, and feature proximity.

Link Prediction

RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations

no code implementations3 Jul 2023 Neha Sahipjohn, Neil Shah, Vishal Tambrahalli, Vineet Gandhi

Significant progress has been made in speaker dependent Lip-to-Speech synthesis, which aims to generate speech from silent videos of talking faces.

Speaker-Specific Lip to Speech Synthesis Speech Synthesis

CARL-G: Clustering-Accelerated Representation Learning on Graphs

no code implementations12 Jun 2023 William Shiao, Uday Singh Saini, Yozen Liu, Tong Zhao, Neil Shah, Evangelos E. Papalexakis

CARL-G is adaptable to different clustering methods and CVIs, and we show that with the right choice of clustering method and CVI, CARL-G outperforms node classification baselines on 4/5 datasets with up to a 79x training speedup compared to the best-performing baseline.

Clustering Contrastive Learning +4

Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?

1 code implementation NeurIPS 2023 Haitao Mao, Zhikai Chen, Wei Jin, Haoyu Han, Yao Ma, Tong Zhao, Neil Shah, Jiliang Tang

Recent studies on Graph Neural Networks(GNNs) provide both empirical and theoretical evidence supporting their effectiveness in capturing structural patterns on both homophilic and certain heterophilic graphs.

Node Classification

MParrotTTS: Multilingual Multi-speaker Text to Speech Synthesis in Low Resource Setting

no code implementations19 May 2023 Neil Shah, Vishal Tambrahalli, Saiteja Kosgi, Niranjan Pedanekar, Vineet Gandhi

We present MParrotTTS, a unified multilingual, multi-speaker text-to-speech (TTS) synthesis model that can produce high-quality speech.

Speech Synthesis Text-To-Speech Synthesis

Link Prediction with Non-Contrastive Learning

1 code implementation25 Nov 2022 William Shiao, Zhichun Guo, Tong Zhao, Evangelos E. Papalexakis, Yozen Liu, Neil Shah

In this work, we extensively evaluate the performance of existing non-contrastive methods for link prediction in both transductive and inductive settings.

Contrastive Learning Link Prediction +2

A Practical, Progressively-Expressive GNN

1 code implementation18 Oct 2022 Lingxiao Zhao, Louis Härtel, Neil Shah, Leman Akoglu

Our model is practical and progressively-expressive, increasing in power with k and c. We demonstrate effectiveness on several benchmark datasets, achieving several state-of-the-art results with runtime and memory usage applicable to practical graphs.

Graph Learning Isomorphism Testing

Forget Unlearning: Towards True Data-Deletion in Machine Learning

no code implementations17 Oct 2022 Rishav Chourasia, Neil Shah

Unlearning algorithms aim to remove deleted data's influence from trained models at a cost lower than full retraining.

Machine Unlearning

Linkless Link Prediction via Relational Distillation

no code implementations11 Oct 2022 Zhichun Guo, William Shiao, Shichang Zhang, Yozen Liu, Nitesh V. Chawla, Neil Shah, Tong Zhao

In this work, to combine the advantages of GNNs and MLPs, we start with exploring direct knowledge distillation (KD) methods for link prediction, i. e., predicted logit-based matching and node representation-based matching.

Knowledge Distillation Link Prediction +1

Empowering Graph Representation Learning with Test-Time Graph Transformation

1 code implementation7 Oct 2022 Wei Jin, Tong Zhao, Jiayuan Ding, Yozen Liu, Jiliang Tang, Neil Shah

In this work, we provide a data-centric view to tackle these issues and propose a graph transformation framework named GTrans which adapts and refines graph data at test time to achieve better performance.

Drug Discovery Graph Representation Learning +1

Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization

1 code implementation5 Oct 2022 Mingxuan Ju, Tong Zhao, Qianlong Wen, Wenhao Yu, Neil Shah, Yanfang Ye, Chuxu Zhang

Besides, we observe that learning from multiple philosophies enhances not only the task generalization but also the single task performances, demonstrating that PARETOGNN achieves better task generalization via the disjoint yet complementary knowledge learned from different philosophies.

Link Prediction Node Classification +4

Flashlight: Scalable Link Prediction with Effective Decoders

no code implementations17 Sep 2022 Yiwei Wang, Bryan Hooi, Yozen Liu, Tong Zhao, Zhichun Guo, Neil Shah

However, HadamardMLP lacks the scalability for retrieving top scoring neighbors on large graphs, since to the best of our knowledge, there does not exist an algorithm to retrieve the top scoring neighbors for HadamardMLP decoders in sublinear complexity.

Graph Learning Link Prediction

Are Message Passing Neural Networks Really Helpful for Knowledge Graph Completion?

1 code implementation21 May 2022 Juanhui Li, Harry Shomer, Jiayuan Ding, Yiqi Wang, Yao Ma, Neil Shah, Jiliang Tang, Dawei Yin

This suggests a conflation of scoring function design, loss function design, and MP in prior work, with promising insights regarding the scalability of state-of-the-art KGC methods today, as well as careful attention to more suitable MP designs for KGC tasks tomorrow.

Graph Data Augmentation for Graph Machine Learning: A Survey

1 code implementation17 Feb 2022 Tong Zhao, Wei Jin, Yozen Liu, Yingheng Wang, Gang Liu, Stephan Günnemann, Neil Shah, Meng Jiang

Overall, our work aims to clarify the landscape of existing literature in graph data augmentation and motivates additional work in this area, providing a helpful resource for researchers and practitioners in the broader graph machine learning domain.

BIG-bench Machine Learning Data Augmentation

GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games

1 code implementation28 Jan 2022 Shichang Zhang, Yozen Liu, Neil Shah, Yizhou Sun

Explaining machine learning models is an important and increasingly popular area of research interest.

Attribute Feature Importance +4

Imbalanced Graph Classification via Graph-of-Graph Neural Networks

2 code implementations1 Dec 2021 Yu Wang, Yuying Zhao, Neil Shah, Tyler Derr

To this end, we introduce a novel framework, Graph-of-Graph Neural Networks (G$^2$GNN), which alleviates the graph imbalance issue by deriving extra supervision globally from neighboring graphs and locally from stochastic augmentations of graphs.

Graph Classification Node Classification

Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation

1 code implementation ICLR 2022 Shichang Zhang, Yozen Liu, Yizhou Sun, Neil Shah

Conversely, multi-layer perceptrons (MLPs) have no graph dependency and infer much faster than GNNs, even though they are less accurate than GNNs for node classification in general.

Knowledge Distillation Node Classification +2

Graph Condensation for Graph Neural Networks

2 code implementations ICLR 2022 Wei Jin, Lingxiao Zhao, Shichang Zhang, Yozen Liu, Jiliang Tang, Neil Shah

Given the prevalence of large-scale graphs in real-world applications, the storage and time for training neural models have raised increasing concerns.

From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness

2 code implementations ICLR 2022 Lingxiao Zhao, Wei Jin, Leman Akoglu, Neil Shah

We choose the subgraph encoder to be a GNN (mainly MPNNs, considering scalability) to design a general framework that serves as a wrapper to up-lift any GNN.

Graph Neural Network

Is Homophily a Necessity for Graph Neural Networks?

no code implementations ICLR 2022 Yao Ma, Xiaorui Liu, Neil Shah, Jiliang Tang

We find that this claim is not quite true, and in fact, GCNs can achieve strong performance on heterophilous graphs under certain conditions.

Node Classification

Automated Self-Supervised Learning for Graphs

1 code implementation ICLR 2022 Wei Jin, Xiaorui Liu, Xiangyu Zhao, Yao Ma, Neil Shah, Jiliang Tang

Then we propose the AutoSSL framework which can automatically search over combinations of various self-supervised tasks.

Clustering Node Classification +2

Sketch-Based Anomaly Detection in Streaming Graphs

1 code implementation8 Jun 2021 Siddharth Bhatia, Mohit Wadhwa, Kenji Kawaguchi, Neil Shah, Philip S. Yu, Bryan Hooi

This higher-order sketch has the useful property of preserving the dense subgraph structure (dense subgraphs in the input turn into dense submatrices in the data structure).

Anomaly Detection Intrusion Detection

Identifying Misinformation from Website Screenshots

no code implementations15 Feb 2021 Sara Abdali, Rutuja Gurav, Siddharth Menon, Daniel Fonseca, Negin Entezari, Neil Shah, Evangelos E. Papalexakis

To capture this overall look, we take screenshots of news articles served by either misinformative or trustworthy web domains and leverage a tensor decomposition based semi-supervised classification technique.

Image Classification Misinformation +2

KNH: Multi-View Modeling with K-Nearest Hyperplanes Graph for Misinformation Detection

no code implementations15 Feb 2021 Sara Abdali, Neil Shah, Evangelos E. Papalexakis

In this work, we introduce a novel generalization of graphs i. e., K-Nearest Hyperplanes graph (KNH) where the nodes are defined by higher order Euclidean subspaces for multi-view modeling of the nodes.


FairOD: Fairness-aware Outlier Detection

1 code implementation5 Dec 2020 Shubhranshu Shekhar, Neil Shah, Leman Akoglu

Fairness and Outlier Detection (OD) are closely related, as it is exactly the goal of OD to spot rare, minority samples in a given population.

Fairness Outlier Detection

The Devil is in the Details: Evaluating Limitations of Transformer-based Methods for Granular Tasks

1 code implementation COLING 2020 Brihi Joshi, Neil Shah, Francesco Barbieri, Leonardo Neves

Contextual embeddings derived from transformer-based neural language models have shown state-of-the-art performance for various tasks such as question answering, sentiment analysis, and textual similarity in recent years.

Question Answering Sentiment Analysis

Action Sequence Augmentation for Early Graph-based Anomaly Detection

1 code implementation20 Oct 2020 Tong Zhao, Bo Ni, Wenhao Yu, Zhichun Guo, Neil Shah, Meng Jiang

With Eland, anomaly detection performance at an earlier stage is better than non-augmented methods that need significantly more observed data by up to 15% on the Area under the ROC curve.

Data Augmentation Graph Anomaly Detection

A Unified View on Graph Neural Networks as Graph Signal Denoising

1 code implementation5 Oct 2020 Yao Ma, Xiaorui Liu, Tong Zhao, Yozen Liu, Jiliang Tang, Neil Shah

In this work, we establish mathematically that the aggregation processes in a group of representative GNN models including GCN, GAT, PPNP, and APPNP can be regarded as (approximately) solving a graph denoising problem with a smoothness assumption.

Denoising Graph Neural Network

Data Augmentation for Graph Neural Networks

2 code implementations11 Jun 2020 Tong Zhao, Yozen Liu, Leonardo Neves, Oliver Woodford, Meng Jiang, Neil Shah

Our work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra-class edges and demote inter-class edges in given graph structure, and our main contribution introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction.

Data Augmentation General Classification +1

Semi-Supervised Multi-aspect Detection of Misinformation using Hierarchical Joint Decomposition

1 code implementation8 May 2020 Sara Abdali, Neil Shah, Evangelos E. Papalexakis

Distinguishing between misinformation and real information is one of the most challenging problems in today's interconnected world.


Minority Reports Defense: Defending Against Adversarial Patches

no code implementations28 Apr 2020 Michael McCoyd, Won Park, Steven Chen, Neil Shah, Ryan Roggenkemper, Minjune Hwang, Jason Xinyu Liu, David Wagner

We propose a defense against patch attacks based on partially occluding the image around each candidate patch location, so that a few occlusions each completely hide the patch.

Adversarial Attack General Classification +1

SliceNDice: Mining Suspicious Multi-attribute Entity Groups with Multi-view Graphs

1 code implementation19 Aug 2019 Hamed Nilforoshan, Neil Shah

Given the reach of web platforms, bad actors have considerable incentives to manipulate and defraud users at the expense of platform integrity.

Attribute Graph Mining

Did We Get It Right? Predicting Query Performance in E-commerce Search

no code implementations1 Aug 2018 Rohan Kumar, Mohit Kumar, Neil Shah, Christos Faloutsos

In this paper, we address the problem of evaluating whether results served by an e-commerce search engine for a query are good or not.

Semi-supervised Content-based Detection of Misinformation via Tensor Embeddings

no code implementations24 Apr 2018 Gisel Bastidas Guacho, Sara Abdali, Neil Shah, Evangelos E. Papalexakis

Most existing works on this topic focus on manual feature extraction and supervised classification models leveraging a large number of labeled (fake or real) articles.

Misinformation Tensor Decomposition

False Information on Web and Social Media: A Survey

3 code implementations23 Apr 2018 Srijan Kumar, Neil Shah

False information can be created and spread easily through the web and social media platforms, resulting in widespread real-world impact.

Feature Engineering Graph Mining

The Many Faces of Link Fraud

no code implementations5 Apr 2017 Neil Shah, Hemank Lamba, Alex Beutel, Christos Faloutsos

Most past work on social network link fraud detection tries to separate genuine users from fraudsters, implicitly assuming that there is only one type of fraudulent behavior.

Fraud Detection

FLOCK: Combating Astroturfing on Livestreaming Platforms

no code implementations4 Oct 2016 Neil Shah

Livestreaming platforms have become increasingly popular in recent years as a means of sharing and advertising creative content.

BIRDNEST: Bayesian Inference for Ratings-Fraud Detection

no code implementations19 Nov 2015 Bryan Hooi, Neil Shah, Alex Beutel, Stephan Gunnemann, Leman Akoglu, Mohit Kumar, Disha Makhija, Christos Faloutsos

To combine these 2 approaches, we formulate our Bayesian Inference for Rating Data (BIRD) model, a flexible Bayesian model of user rating behavior.

Bayesian Inference Fraud Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.