SENSE enhances node sequences in graphs using vector embeddings.
problem Efficiently capturing graph node sequences for applications.
method SENSE-S learns node embeddings and composes them for sequences, preserving node order.
result SENSE-S increases multi-label classification and link-prediction accuracy by up to 50% and 78% respectively.
A new method for fast graph embedding using diffusion graphs.
problem Efficiently generating graph embeddings for large networks.
method Diffusion graphs for rapid vertex sequence generation.
result Improved accuracy and performance with higher edge density.
Graph2Seq converts graph inputs to sequences with attention-based neural networks.
problem Converting graph inputs to sequences for machine learning tasks.
method Graph-to-sequence neural encoder-decoder model with attention-based LSTM.
result Achieves state-of-the-art performance on various tasks.
Predicts node sequences in graphs using multi-order network models.
problem Predicting sequences of node traversals in graphs.
method Combines multiple higher-order network models into a multi-order model, fitting and selecting the optimal maximum order.
result Outperforms state-of-the-art algorithms for next-element and full sequence prediction.
New approach learns graph-level representations using RNNs and node sequences.
problem Learning graph-level representations efficiently and accurately.
method Combines unsupervised and supervised learning; uses Gumbel-Softmax for node sequences and RNN for neighborhood information.
result Superior or comparable performance on graph classification benchmarks.
GTEA learns node representations in temporal interaction graphs.
problem Inductive representation learning on temporal interaction graphs.
method Integrates sequence model with time encoder and self-attention scheme for edge and node embeddings.
result GTEA learns comprehensive node representations capturing temporal and structural characteristics.
New models for graph sequences capture link and community persistence.
problem Difficulties in extending block model results to graph sequences.
method Two models for graph sequences capturing link and community persistence, with efficient inference algorithms.
result Validated suitability of proposed models and methods on synthetic and real instances.
GGP models multivariate time series with latent sub-sequences for diverse behaviors.
problem Modeling multivariate time series with diverse behaviors and patterns.
method Graph Gamma Process (GGP) linear dynamical systems with latent sub-sequences.
result GGP models exhibit good predictive performance and reveal interpretable latent patterns.
Model tags biomedical texts with tree-structured tags.
problem Tagging unstructured texts with an arbitrary number of terms from an ontology.
method Neural tree decoding approach starting from the root node of an ontology.
result Outperforms state-of-the-art approaches on MeSH term assignment.
From a sequence of similarity networks, with edges representing certain similarity measures between nodes, we are interested in detecting a change-point which changes the statistical property of the networks. After the change, a subset of anomalous nodes which compares dissimilarly with the normal nodes. We study a sim…
Enhances node embeddings in networks using topic modeling.
problem Learning effective node embeddings in network structures.
method Introduces a framework that assigns each node a topic and generates enhanced community representations.
result The method outperforms baseline NRL methods in node classification and link prediction tasks.
New method learns dynamic node embeddings from temporal networks.
problem Temporal networks' temporal information is often ignored or approximated.
method Continuous-time dynamic network embeddings (CTDNEs) using temporal walks.
result CTDNEs achieve an average gain of 11.9% in AUC across all methods and graphs.
An analytic approach and description are presented for the moduli cotangent sheaf for suitable stable curve families including noded fibers. For sections of the square of the relative dualizing sheaf, the residue map at a node gives rise to an exact sequence. The residue kernel defines the vanishing residue subsheaf. F…
New model optimizes oil product distribution via pipelines.
problem Optimizing oil product distribution via pipelines.
method Discrete-time mixed integer linear programming model.
result Significant reductions in pipeline operational cost.
DVE models dynamic changes in feature embeddings for better sequence-aware applications.
problem Dynamic characterization of feature variations in time-varying data.
method Dynamic Variational Embedding (DVE) using recurrent neural networks.
result DVE models intrinsic nature and temporal variation of nodes effectively.
New model generates graphs with tighter likelihood bounds and better quality.
problem Intractable likelihood of autoregressive graph models.
method Derive exact joint probability, approximate node orderings, variational inference.
result Lower bound on log-likelihood is significantly tighter than previous methods.
New results on inferring hidden states in trackable weak models.
problem Inferring hidden states in trackable weak models.
method Analyzing strongly-connected trackable weak models and reconstructing branch choices.
result The number of hypotheses in strongly-connected trackable models is bounded by a constant.
In this paper, we formulate and prove a general compactness theorem for harmonic maps using Deligne-Mumford moduli space and families of curves. The main theorem shows that given a sequence of harmonic maps over a sequence of complex curves, there is a family of curves and a subsequence such that both the domains and t…
A new network embedding method using diffusion to overcome limitations of random walks.
problem Limitations of random walk based network embedding methods in fragile sampling and disequilibrium networks.
method Proposes a network diffusion based embedding method that captures both depth and breadth information and uses cascades for global network information.
result The diffusion based models are more robust in fragile sampling and highly imbalanced networks.
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.…
Reconstructing weighted networks from partial information is necessary in many important circumstances, e.g. for a correct estimation of systemic risk. It has been shown that, in order to achieve an accurate reconstruction, it is crucial to reliably replicate the empirical degree sequence, which is however unknown in m…
Unified model generates representations for all nodes in growing graphs.
problem Cold start problem in growing graphs isolates new nodes.
method Generative graph convolutional network that learns adaptive node representations.
result Superior performance on citation network datasets.
Framework learns dynamic graph attributes and links co-evolution.
problem Forecasting change of node attributes and link formation in dynamic graphs.
method CoEvoGNN framework with temporal self-attention and joint optimization.
result Framework outperforms baselines on predicting unseen graph snapshots.
New insights into neural network forgetting reveal a trade-off between node activation and re-use.
problem Challenges in maintaining performance on old tasks while learning new ones.
method Theoretical analysis of synthetic and real data setups, focusing on node activation vs re-use.
result Worst forgetting occurs in an intermediate similarity regime between learned tasks.
Paper proposes AR model for graph sequences.
problem Predicting sequences of graphs with variable topology.
method Formalizes AR model for graphs using GNN to learn and predict next graph.
result Significantly better performance on synthetic graph generation problems.
Bidirectional sequence generation improves performance in conversational tasks.
problem Neural sequence generation typically considers only past tokens, limiting performance.
method Introduced placeholder tokens that can consider both past and future tokens in sequence generation.
result Bidirectional model outperforms competitive baselines on conversational tasks.
This paper improves node classification using graph structure and side information.
problem Improving node classification in semi-supervised scenarios.
method Combines graph convolutional networks with extracted side information.
result The proposed model achieves higher prediction accuracy.
StackSeq2Seq improves route finding on graphs using deep neural networks.
problem Finding the shortest path between graph nodes.
method Dual Encoder Seq2Seq architecture, context vector, homotopy continuation.
result Increased accuracy in learning shortest routes on graphs.
NCRF transducers improve sequence labeling across tasks.
problem Sequence labeling with non-linear node potentials.
method Two RNNs: one for features and one for long-range label dependencies.
result Consistent improvements over linear-chain NCRFs and RNN transducers.
The paper introduces a new method for graph embedding using exponential family distributions.
problem Representing networks in a low dimensional latent space for various applications.
method Introduces the exponential family graph embedding model, generalizing random walk-based techniques to exponential family conditional distributions.
result The proposed techniques outperform existing methods in link prediction and node classification tasks.
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 …
The paper proposes a method to infer differentiation trees from RNA velocity data.
problem Reconstructing dynamic cellular processes from sequencing data.
method Defining varifold distances between RNA velocity curves to approximate shortest-path distances in a tree.
result The varifold distance method approximates the shortest-path distance in a tree isomorphic to the target differentiation tree.
We present the mixture-of-parents maximum entropy Markov model (MoP-MEMM), a class of directed graphical models extending MEMMs. The MoP-MEMM allows tractable incorporation of long-range dependencies between nodes by restricting the conditional distribution of each node to be a mixture of distributions given the parent…
EvolveGCN adapts GCN for dynamic graphs without node embeddings.
problem Learning graph dynamics with frequent node set changes.
method Adapts GCN using RNN to evolve parameters without node embeddings.
result Generally higher performance on link prediction, edge classification, and node classification tasks.
Graph classification model learns sequentially from graph structure.
problem Graph classification based on structural information.
method Sequential embedding and variational regularization.
result State-of-the-art classification results on molecular datasets.
PROPS personalizes complex models for sequential data.
problem Personalizing complex models for sequential data.
method Pin black-box predictions to a hidden Markov model and learn probabilistic perturbations.
result PROPS achieves good customization with minimal data.
AutoGraph uses transformers to efficiently generate graphs as sequences.
problem Efficiently generating large, sparse graphs without expensive node features.
method Flattening graphs into sequences and using decoder-only transformers.
result AutoGraph achieves state-of-the-art performance on synthetic and molecular benchmarks.
Efficient algorithm for self-directed learning of convex clusters on graphs.
problem Self-directed classification of nodes on graphs with convex clusters.
method Developed efficient algorithms for (geodesically) convex clusters on graphs.
result Polynomial runtime algorithm with 3(h(G)+1)4lnn mistakes for graphs with two convex clusters. A new model captures diffusion dynamics in networks using hidden states.
problem Capturing temporal relationships and hidden content trajectories in network diffusion.
method A topological recurrent neural model that embeds diffusion history as hidden states.
result Good experimental performances for diffusion modeling and prediction.
Deep neural networks approximate solutions to NP-hard problems.
problem Approximating solutions to NP-hard combinatorial optimization problems.
method Homotopic recurrent neural networks combined with reinforcement learning.
result Homotopic RNNs improve the quality of solutions compared to vanilla RNNs.
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≥4. In this article, we study various induced subgraphs of this graph. In particular, we prove tha…
Paper studies distributed learning with limited communication bits, achieving optimal error exponents.
problem Distributed hypothesis testing with constant communication bits.
method Geometric approach in distribution spaces, encoding empirical distributions to transmission bits.
result Optimal achievable error exponents and coding schemes for various communication constraints.
ISP improves GNN expressivity by stratifying nodes based on graph invariants.
problem Graph Neural Networks struggle with expressivity and structural heterogeneity.
method Invariant-Stratified Propagation (ISP) using ISP-WL and ISPGNN.
result ISP achieves enhanced expressivity beyond 1-WL, with theoretical guarantees and practical improvements.
ER-GNN uses experience replay to prevent GNNs from forgetting previous tasks.
problem Catastrophic forgetting in GNNs when learning multiple tasks sequentially.
method Experience Replay framework to store and replay knowledge from previous tasks.
result ER-GNN effectively mitigates catastrophic forgetting in GNNs.
A new method for learning network representations that avoids information bias and sparsity.
problem Information bias and sparsity in network representation learning.
method A spreading-activation schema for learning node embeddings in network structures.
result Significant improvement in various real-world network analysis tasks.
New edge features improve GNN performance in biological datasets.
problem Inefficient use of edge features in GNNs.
method Self-supervised and unsupervised learning for new edge features, incorporating Forman-Ricci curvature.
result Improved node classification performance over baseline GNN models.
New models capture heterogeneous network density, improving community detection.
problem Empirical networks are often globally sparse but locally dense.
method Latent Poisson models generating hidden multigraphs.
result These models improve community detection in sparse networks.
A new framework predicts links in time-dependent networks using Bernoulli autoregression.
problem Predicting links in time-dependent networks with additional auxiliary information.
method A Bernoulli autoregressive model with regularization for link discovery.
result The model can discover new links not present in the data.