arXiv research

SENSE enhances node sequences in graphs using vector embeddings.

A new method for fast graph embedding using diffusion graphs.

The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant challenge in achieving accurate conversion from graph form …

GTEA learns node representations in temporal interaction graphs.

Predicts node sequences in graphs using multi-order network models.

New model generates graphs with tighter likelihood bounds and better quality.

Although the computational and statistical trade-off for modeling single graphs, for instance, using block models is relatively well understood, extending such results to sequences of graphs has proven to be difficult. In this work, we take a step in this direction by proposing two models for graph sequences that captu…

Modeling generative process of growing graphs has wide applications in social networks and recommendation systems, where cold start problem leads to new nodes isolated from existing graph. Despite the emerging literature in learning graph representation and graph generation, most of them can not handle isolated new nod…

Framework learns dynamic graph attributes and links co-evolution.

We consider the two problems of predicting links in a dynamic graph sequence and predicting functions defined at each node of the graph. In many applications, the solution of one problem is useful for solving the other. Indeed, if these functions reflect node features, then they are related through the graph structure.…

GGP models multivariate time series with latent sub-sequences for diverse behaviors.

This paper proposes an autoregressive (AR) model for sequences of graphs, which generalises traditional AR models. A first novelty consists in formalising the AR model for a very general family of graphs, characterised by a variable topology, and attributes associated with nodes and edges. A graph neural network (GNN) …

This paper improves node classification using graph structure and side information.

A known failing of many popular random graph models is that the Aldous-Hoover Theorem guarantees these graphs are dense with probability one; that is, the number of edges grows quadratically with the number of nodes. This behavior is considered unrealistic in observed graphs. We define a notion of edge exchangeability …

Recently a variety of methods have been developed to encode graphs into low-dimensional vectors that can be easily exploited by machine learning algorithms. The majority of these methods start by embedding the graph nodes into a low-dimensional vector space, followed by using some scheme to aggregate the node embedding…

A widely studied non-deterministic polynomial time (NP) hard problem lies in finding a route between the two nodes of a graph. Often meta-heuristics algorithms such as $A^{*}$ are employed on graphs with a large number of nodes. Here, we propose a deep recurrent neural network architecture based on the Sequence-2-Seque…

AutoGraph uses transformers to efficiently generate graphs as sequences.

Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Such temporal networks (or edge streams) consist of a sequence of timestamped edges and are seemingly ubiquitous. Despite the importance of accurately modeling the temporal information, most embedding methods ignore it …

The paper introduces a new method for graph embedding using exponential family distributions.

Paper converts graph learning to lifelong learning.

Graph representation learning resurges as a trending research subject owing to the widespread use of deep learning for Euclidean data, which inspire various creative designs of neural networks in the non-Euclidean domain, particularly graphs. With the success of these graph neural networks (GNN) in the static setting, …

We address the problem of graph classification based only on structural information. Inspired by natural language processing techniques (NLP), our model sequentially embeds information to estimate class membership probabilities. Besides, we experiment with NLP-like variational regularization techniques, making the mode…

ER-GNN uses experience replay to prevent GNNs from forgetting previous tasks.

Graph Hawkes Neural Network forecasts evolving graph sequences.

Efficient algorithm for self-directed learning of convex clusters on graphs.

ISP improves GNN expressivity by stratifying nodes based on graph invariants.

Novel graph neural network combines random walks with local message passing.

Graphs evolve; GNNs learn from past tasks.

New edge features improve GNN performance in biological datasets.

It is well-known that the Pachner graph of $n$-vertex triangulated $2$-spheres is connected, i.e., each pair of $n$-vertex triangulated $2$-spheres can be turned into each other by a sequence of edge flips for each $n\geq 4$. In this article, we study various induced subgraphs of this graph. In particular, we prove tha…

Two architectures that generalize convolutional neural networks (CNNs) for the processing of signals supported on graphs are introduced. We start with the selection graph neural network (GNN), which replaces linear time invariant filters with linear shift invariant graph filters to generate convolutional features and r…

New results on inferring hidden states in trackable weak models.

Online health communities such as the online breast cancer forum enable patients (i.e., users) to interact and help each other within various subforums, which are subsections of the main forum devoted to specific health topics. The changing nature of the users' activities in different subforums can be strong indicators…

TG-GAN models dynamic graph evolution for continuous-time temporal graphs.

A method to generate long-range human actions by leveraging graph convolutional networks and self-attention.

Much combinatorial optimisation problems constitute a non-polynomial (NP) hard optimisation problem, i.e., they can not be solved in polynomial time. One such problem is finding the shortest route between two nodes on a graph. Meta-heuristic algorithms such as $A^{*}$ along with mixed-integer programming (MIP) methods …

gLSTM improves graph neural networks by increasing storage capacity to prevent over-squashing.

We consider the problem of path inference: given a path prefix, i.e., a partially observed sequence of nodes in a graph, we want to predict which nodes are in the missing suffix. In particular, we focus on natural paths occurring as a by-product of the interaction of an agent with a network---a driver on the transporta…

Proposes GIL for semi-supervised graph classification.

A new method improves node classification in graphs with limited labels.

Graph neural networks benefit from node features but struggle with featureless graphs.

Neural sequence generation is typically performed token-by-token and left-to-right. Whenever a token is generated only previously produced tokens are taken into consideration. In contrast, for problems such as sequence classification, bidirectional attention, which takes both past and future tokens into consideration, …

HDGI learns node representations for heterogeneous graphs.

Graph embedding is an important approach for graph analysis tasks such as node classification and link prediction. The goal of graph embedding is to find a low dimensional representation of graph nodes that preserves the graph information. Recent methods like Graph Convolutional Network (GCN) try to consider node attri…

HYPA-DBGNN detects anomalous sequential patterns in temporal graphs.

Graph Posterior Network improves uncertainty estimation for node classification in interdependent graphs.

Proposes a graph pooling method leveraging node proximity for hierarchical graph representation learning.

PGNs dynamically infer and use graph structures to improve model generalization.