Search Results for author: Marinka Zitnik

Found 49 papers, 31 papers with code

Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation

1 code implementation5 Dec 2023 Shanshan Zhong, Zhongzhan Huang, ShangHua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou

To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus is suitable for LoT study.

Logical Reasoning

Graph AI in Medicine

no code implementations20 Oct 2023 Ruth Johnson, Michelle M. Li, Ayush Noori, Owen Queen, Marinka Zitnik

With diverse data -- from patient records to imaging -- GNNs process data holistically by viewing modalities as nodes interconnected by their relationships.

Decision Making Graph Representation Learning +1

Full-Atom Protein Pocket Design via Iterative Refinement

1 code implementation NeurIPS 2023 Zaixi Zhang, Zepu Lu, Zhongkai Hao, Marinka Zitnik, Qi Liu

In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions.

A Systematic Survey in Geometric Deep Learning for Structure-based Drug Design

no code implementations20 Jun 2023 Zaixi Zhang, Jiaxian Yan, Qi Liu, Enhong Chen, Marinka Zitnik

Recent developments in geometric deep learning, focusing on the integration and processing of 3D geometric data, coupled with the availability of accurate protein 3D structure predictions from tools like AlphaFold, have greatly advanced the field of structure-based drug design.

Benchmarking Drug Discovery +1

GNNDelete: A General Strategy for Unlearning in Graph Neural Networks

1 code implementation26 Feb 2023 Jiali Cheng, George Dasoulas, Huan He, Chirag Agarwal, Marinka Zitnik

Deleted Edge Consistency ensures that the influence of deleted elements is removed from both model weights and neighboring representations, while Neighborhood Influence guarantees that the remaining model knowledge is preserved after deletion.

Domain Adaptation for Time Series Under Feature and Label Shifts

1 code implementation6 Feb 2023 Huan He, Owen Queen, Teddy Koker, Consuelo Cuevas, Theodoros Tsiligkaridis, Marinka Zitnik

Additionally, the label distributions of tasks in the source and target domains can differ significantly, posing difficulties in addressing label shifts and recognizing labels unique to the target domain.

Time Series Time Series Analysis +3

Multimodal learning with graphs

no code implementations7 Sep 2022 Yasha Ektefaie, George Dasoulas, Ayush Noori, Maha Farhat, Marinka Zitnik

Artificial intelligence for graphs has achieved remarkable success in modeling complex systems, ranging from dynamic networks in biology to interacting particle systems in physics.

Graph Learning Inductive Bias +1

Evaluating Explainability for Graph Neural Networks

1 code implementation19 Aug 2022 Chirag Agarwal, Owen Queen, Himabindu Lakkaraju, Marinka Zitnik

As post hoc explanations are increasingly used to understand the behavior of graph neural networks (GNNs), it becomes crucial to evaluate the quality and reliability of GNN explanations.

OpenXAI: Towards a Transparent Evaluation of Model Explanations

2 code implementations22 Jun 2022 Chirag Agarwal, Satyapriya Krishna, Eshika Saxena, Martin Pawelczyk, Nari Johnson, Isha Puri, Marinka Zitnik, Himabindu Lakkaraju

OpenXAI comprises of the following key components: (i) a flexible synthetic data generator and a collection of diverse real-world datasets, pre-trained models, and state-of-the-art feature attribution methods, (ii) open-source implementations of twenty-two quantitative metrics for evaluating faithfulness, stability (robustness), and fairness of explanation methods, and (iii) the first ever public XAI leaderboards to benchmark explanations.

Benchmarking Explainable Artificial Intelligence (XAI) +1

Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency

1 code implementation17 Jun 2022 Xiang Zhang, Ziyuan Zhao, Theodoros Tsiligkaridis, Marinka Zitnik

Experiments against eight state-of-the-art methods show that TF-C outperforms baselines by 15. 4% (F1 score) on average in one-to-one settings (e. g., fine-tuning an EEG-pretrained model on EMG data) and by 8. 4% (precision) in challenging one-to-many settings (e. g., fine-tuning an EEG-pretrained model for either hand-gesture recognition or mechanical fault prediction), reflecting the breadth of scenarios that arise in real-world applications.

Domain Adaptation EEG +7

Multimodal Learning on Graphs for Disease Relation Extraction

1 code implementation16 Mar 2022 Yucong Lin, Keming Lu, Sheng Yu, Tianxi Cai, Marinka Zitnik

On a dataset annotated by human experts, REMAP improves text-based disease relation extraction by 10. 0% (accuracy) and 17. 2% (F1-score) by fusing disease knowledge graphs with text information.

Knowledge Graphs Relation Extraction

Rethinking Stability for Attribution-based Explanations

no code implementations14 Mar 2022 Chirag Agarwal, Nari Johnson, Martin Pawelczyk, Satyapriya Krishna, Eshika Saxena, Marinka Zitnik, Himabindu Lakkaraju

As attribution-based explanation methods are increasingly used to establish model trustworthiness in high-stakes situations, it is critical to ensure that these explanations are stable, e. g., robust to infinitesimal perturbations to an input.

Sparse dictionary learning recovers pleiotropy from human cell fitness screens

1 code implementation11 Nov 2021 Joshua Pan, Jason J. Kwon, Jessica A. Talamas, Ashir A. Borah, Francisca Vazquez, Jesse S. Boehm, Aviad Tsherniak, Marinka Zitnik, James M. McFarland, William C. Hahn

In high-throughput functional genomic screens, each gene product is commonly assumed to exhibit a singular biological function within a defined protein complex or pathway.

Dictionary Learning

Graph-Guided Network for Irregularly Sampled Multivariate Time Series

2 code implementations ICLR 2022 Xiang Zhang, Marko Zeman, Theodoros Tsiligkaridis, Marinka Zitnik

Here, we introduce RAINDROP, a graph neural network that embeds irregularly sampled and multivariate time series while also learning the dynamics of sensors purely from observational data.

Time Series Time Series Analysis

Leveraging the Cell Ontology to classify unseen cell types

1 code implementation Nature Communications 2021 Sheng Wang, Angela Oliveira Pisco, Aaron McGeever, Maria Brbic, Marinka Zitnik, Spyros Darmanis, Jure Leskovec, Jim Karkanias, Russ B. Altman

Single cell technologies are rapidly generating large amounts of data that enables us to understand biological systems at single-cell resolution.

Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods

no code implementations16 Jun 2021 Chirag Agarwal, Marinka Zitnik, Himabindu Lakkaraju

As Graph Neural Networks (GNNs) are increasingly being employed in critical real-world applications, several methods have been proposed in recent literature to explain the predictions of these models.


Deep Contextual Learners for Protein Networks

no code implementations4 Jun 2021 Michelle M. Li, Marinka Zitnik

We construct a multi-scale network of the Human Cell Atlas and apply AWARE to learn protein, cell type, and tissue embeddings that uphold cell type and tissue hierarchies.

Graph Representation Learning in Biomedicine

no code implementations11 Apr 2021 Michelle M. Li, Kexin Huang, Marinka Zitnik

Biomedical networks (or graphs) are universal descriptors for systems of interacting elements, from molecular interactions and disease co-morbidity to healthcare systems and scientific knowledge.

BIG-bench Machine Learning Graph Representation Learning

Structure Inducing Pre-Training

1 code implementation18 Mar 2021 Matthew B. A. McDermott, Brendan Yap, Peter Szolovits, Marinka Zitnik

Based on this review, we introduce a descriptive framework for pre-training that allows for a granular, comprehensive understanding of how relational structure can be induced.

Descriptive Inductive Bias +3

Towards a Unified Framework for Fair and Stable Graph Representation Learning

2 code implementations25 Feb 2021 Chirag Agarwal, Himabindu Lakkaraju, Marinka Zitnik

In this work, we establish a key connection between counterfactual fairness and stability and leverage it to propose a novel framework, NIFTY (uNIfying Fairness and stabiliTY), which can be used with any GNN to learn fair and stable representations.

counterfactual Fairness +1

Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development

2 code implementations18 Feb 2021 Kexin Huang, Tianfan Fu, Wenhao Gao, Yue Zhao, Yusuf Roohani, Jure Leskovec, Connor W. Coley, Cao Xiao, Jimeng Sun, Marinka Zitnik

Here, we introduce Therapeutics Data Commons (TDC), the first unifying platform to systematically access and evaluate machine learning across the entire range of therapeutics.

BIG-bench Machine Learning Drug Discovery

MolDesigner: Interactive Design of Efficacious Drugs with Deep Learning

1 code implementation5 Oct 2020 Kexin Huang, Tianfan Fu, Dawood Khan, Ali Abid, Ali Abdalla, Abubakar Abid, Lucas M. Glass, Marinka Zitnik, Cao Xiao, Jimeng Sun

The efficacy of a drug depends on its binding affinity to the therapeutic target and pharmacokinetics.

Subgraph Neural Networks

1 code implementation NeurIPS 2020 Emily Alsentzer, Samuel G. Finlayson, Michelle M. Li, Marinka Zitnik

Deep learning methods for graphs achieve remarkable performance on many node-level and graph-level prediction tasks.

GNNGuard: Defending Graph Neural Networks against Adversarial Attacks

1 code implementation NeurIPS 2020 Xiang Zhang, Marinka Zitnik

Here, we develop GNNGuard, a general algorithm to defend against a variety of training-time attacks that perturb the discrete graph structure.

Graph Meta Learning via Local Subgraphs

1 code implementation NeurIPS 2020 Kexin Huang, Marinka Zitnik

G-Meta learns how to quickly adapt to a new task using only a handful of nodes or edges in the new task and does so by learning from data points in other graphs or related, albeit disjoint label sets.

Few-Shot Learning

Open Graph Benchmark: Datasets for Machine Learning on Graphs

19 code implementations NeurIPS 2020 Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, Jure Leskovec

We present the Open Graph Benchmark (OGB), a diverse set of challenging and realistic benchmark datasets to facilitate scalable, robust, and reproducible graph machine learning (ML) research.

Knowledge Graphs Node Property Prediction

SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks

1 code implementation30 Apr 2020 Kexin Huang, Cao Xiao, Lucas Glass, Marinka Zitnik, Jimeng Sun

Here, we present SkipGNN, a graph neural network approach for the prediction of molecular interactions.

Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19

2 code implementations15 Apr 2020 Deisy Morselli Gysi, Ítalo Do Valle, Marinka Zitnik, Asher Ameli, Xiao Gan, Onur Varol, Susan Dina Ghiassian, JJ Patten, Robert Davey, Joseph Loscalzo, Albert-László Barabási

The current pandemic has highlighted the need for methodologies that can quickly and reliably prioritize clinically approved compounds for their potential effectiveness for SARS-CoV-2 infections.

Strategies for Pre-training Graph Neural Networks

10 code implementations ICLR 2020 Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, Jure Leskovec

Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training.

Graph Classification Molecular Property Prediction +5

GNNExplainer: Generating Explanations for Graph Neural Networks

10 code implementations NeurIPS 2019 Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, Jure Leskovec

We formulate GNNExplainer as an optimization task that maximizes the mutual information between a GNN's prediction and distribution of possible subgraph structures.

BIG-bench Machine Learning Explainable artificial intelligence +2

NIMFA: A Python Library for Nonnegative Matrix Factorization

no code implementations6 Aug 2018 Marinka Zitnik, Blaz Zupan

NIMFA is an open-source Python library that provides a unified interface to nonnegative matrix factorization algorithms.

Embedding Logical Queries on Knowledge Graphs

5 code implementations NeurIPS 2018 William L. Hamilton, Payal Bajaj, Marinka Zitnik, Dan Jurafsky, Jure Leskovec

Learning low-dimensional embeddings of knowledge graphs is a powerful approach used to predict unobserved or missing edges between entities.

Complex Query Answering

Network Enhancement: a general method to denoise weighted biological networks

no code implementations9 May 2018 Bo Wang, Armin Pourshafeie, Marinka Zitnik, Junjie Zhu, Carlos D. Bustamante, Serafim Batzoglou, Jure Leskovec

Networks are ubiquitous in biology where they encode connectivity patterns at all scales of organization, from molecular to the biome.


Prioritizing network communities

no code implementations7 May 2018 Marinka Zitnik, Rok Sosic, Jure Leskovec

Community detection identifies candidate modules as hypotheses, which then need to be validated through experiments, such as mutagenesis in a biological laboratory.

Community Detection

Modeling polypharmacy side effects with graph convolutional networks

1 code implementation2 Feb 2018 Marinka Zitnik, Monica Agrawal, Jure Leskovec

The approach constructs a multimodal graph of protein-protein interactions, drug-protein target interactions, and the polypharmacy side effects, which are represented as drug-drug interactions, where each side effect is an edge of a different type.

Link Prediction

Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning

2 code implementations30 Jan 2018 Xuan Wang, Yu Zhang, Xiang Ren, Yuhao Zhang, Marinka Zitnik, Jingbo Shang, Curtis Langlotz, Jiawei Han

Motivation: State-of-the-art biomedical named entity recognition (BioNER) systems often require handcrafted features specific to each entity type, such as genes, chemicals and diseases.

Feature Engineering Multi-Task Learning +4

Spectral Graph Wavelets for Structural Role Similarity in Networks

no code implementations ICLR 2018 Claire Donnat, Marinka Zitnik, David Hallac, Jure Leskovec

Nodes residing in different parts of a graph can have similar structural roles within their local network topology.

Large-scale analysis of disease pathways in the human interactome

no code implementations3 Dec 2017 Monica Agrawal, Marinka Zitnik, Jure Leskovec

However, we show that higher-order network structures, such as small subgraphs of the pathway, provide a promising direction for the development of new methods.

Learning Structural Node Embeddings Via Diffusion Wavelets

1 code implementation KDD 2018 Claire Donnat, Marinka Zitnik, David Hallac, Jure Leskovec

Nodes residing in different parts of a graph can have similar structural roles within their local network topology.

Jumping across biomedical contexts using compressive data fusion

1 code implementation10 Aug 2017 Marinka Zitnik, Blaz Zupan

Motivation: The rapid growth of diverse biological data allows us to consider interactions between a variety of objects, such as genes, chemicals, molecular signatures, diseases, pathways and environmental exposures.

Predicting multicellular function through multi-layer tissue networks

1 code implementation14 Jul 2017 Marinka Zitnik, Jure Leskovec

We use OhmNet to study multicellular function in a multi-layer protein interaction network of 107 human tissues.

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