Search Results for author:
Found 21 papers, 8 papers with code
When Collaborative Filtering is not Collaborative: Unfairness of PCA for Recommendations
The first negatively impacts less popular items, due to the fact that less popular items rely on trailing latent components to recover their values.
Graph-SCP: Accelerating Set Cover Problems with Graph Neural Networks
We look specifically at the Set Cover Problem (SCP) and propose Graph-SCP, a graph neural network method that can augment existing optimization solvers by learning to identify a much smaller sub-problem that contains the solution space.
GRASP: Accelerating Shortest Path Attacks via Graph Attention
We consider an APX-hard problem, where an adversary aims to attack shortest paths in a graph by removing the minimum number of edges.
Disentangling Node Attributes from Graph Topology for Improved Generalizability in Link Prediction
Our proposed method, UPNA (Unsupervised Pre-training of Node Attributes), solves the inductive link prediction problem by learning a function that takes a pair of node attributes and predicts the probability of an edge, as opposed to Graph Neural Networks (GNN), which can be prone to topological shortcuts in graphs with power-law degree distribution.
Social AI and the Challenges of the Human-AI Ecosystem
In order to understand the impact of AI on socio-technical systems and design next-generation AIs that team with humans to help overcome societal problems rather than exacerbate them, we propose to build the foundations of Social AI at the intersection of Complex Systems, Network Science and AI.
Using Sequences of Life-events to Predict Human Lives
We can also represent human lives in a way that shares this structural similarity to language.
Neuroscience needs Network Science
We explore the challenges and opportunities in integrating multiple data streams for understanding the neural transitions from development to healthy function to disease, and discuss the potential for collaboration between network science and neuroscience communities.
CELEST: Federated Learning for Globally Coordinated Threat Detection
In this study, we propose CELEST (CollaborativE LEarning for Scalable Threat detection, a federated machine learning framework for global threat detection over HTTP, which is one of the most commonly used protocols for malware dissemination and communication.
AI-Bind: Improving Binding Predictions for Novel Protein Targets and Ligands
Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery.
RAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunity
We present RAWLSNET, a system for altering Bayesian Network (BN) models to satisfy the Rawlsian principle of fair equality of opportunity (FEO).
Optimizing Graph Structure for Targeted Diffusion
However, in many applications, such as targeted vulnerability assessment or clinical therapies, one aspires to affect a targeted subset of a network, while limiting the impact on the rest.
Social and Information Networks Physics and Society
The why, how, and when of representations for complex systems
At each step we consider different types of \emph{dependencies}; these are properties of the system that describe how the existence of one relation among the parts of a system may influence the existence of another relation.
Social and Information Networks Discrete Mathematics Quantitative Methods 68R10
Topological Effects on Attacks Against Vertex Classification
Vertex classification is vulnerable to perturbations of both graph topology and vertex attributes, as shown in recent research.
Understanding the Limitations of Network Online Learning
We call this querying process Network Online Learning and present a family of algorithms called NOL*.
Selective Network Discovery via Deep Reinforcement Learning on Embedded Spaces
As a result, network discovery algorithms optimized for specific downstream learning tasks given resource collection constraints are of great interest.
L2P: Learning to Place for Estimating Heavy-Tailed Distributed Outcomes
In its placing phase, L2P obtains a prediction by placing the new instance among the known instances.
On Designing Machine Learning Models for Malicious Network Traffic Classification
Machine learning (ML) started to become widely deployed in cyber security settings for shortening the detection cycle of cyber attacks.
Detecting Path Anomalies in Time Series Data on Networks
Anomaly detection has been extensively studied in categorical sequences, however we often have access to time series data that contain paths through networks.
Social and Information Networks Physics and Society
GLEE: Geometric Laplacian Eigenmap Embedding
Graph embedding seeks to build a low-dimensional representation of a graph G. This low-dimensional representation is then used for various downstream tasks.
Some Advances in Role Discovery in Graphs
Role discovery in graphs is an emerging area that allows analysis of complex graphs in an intuitive way.
NetSimile: A Scalable Approach to Size-Independent Network Similarity
Having such features will enable a wealth of graph mining tasks, including clustering, outlier detection, visualization, etc.
Social and Information Networks Physics and Society Applications
