Paper tackles graph matching with partially correct seeds, improving performance guarantees.
problem Graph matching with partially correct seeds.
method Proposes algorithms for matching vertices based on 1-hop and 2-hop neighborhoods, analyzing their performance guarantees.
result New 2-hop algorithm requires fewer correct seeds than the 1-hop algorithm, especially for sparse graphs.
CLuP achieves near optimal ground state energies for positive and negative Hopfield models.
problem Finding near optimal ground state energies for positive and negative Hopfield models.
method Controlled Loosening-up (CLuP) algorithm with fully lifted random duality theory (fl RDT).
result Achieves ground state free energies of 1.77 1.77 1.77 and 0.33 0.33 0.33 for positive and negative Hopfield models respectively. Develops HOPS for non-smooth problems with improved complexity.
problem Solving non-smooth optimization problems with explicit max-structure.
method Combines Nesterov's smoothing and accelerated gradient methods.
result Achieved lower iteration complexity of O ~ ( 1 / ε 1 − θ ) \widetilde O(1/ε^{1-θ}) O ( 1/ ε 1 − θ ) . Proposes a differentiable STFT for more efficient optimization of hop length.
problem Efficient optimization of hop length in STFT for better temporal control.
method Introduces a differentiable version of STFT with continuous hop length.
result Improves optimization methods like gradient descent for STFT.
HopGAT improves node classification in sparsely labeled graphs by learning from distant neighbors.
problem Classifying nodes in sparsely labeled graphs with limited labeled data.
method Hop-aware supervision mechanism and simulated annealing learning strategy.
result The model achieves high accuracy even with 40% labeled data, reducing performance loss to 3.9%.
k-hop GNNs improve GNNs' ability to identify graph properties.
problem GNNs' limitations in identifying fundamental graph properties.
method Proposes k-hop GNNs that aggregate information from a node's k-hop neighborhood.
result k-hop GNNs can identify fundamental graph properties.
Efficient neural models for complex multi-hop reasoning tasks.
problem Complex multi-hop reasoning tasks in large knowledge bases.
method Differentiable neural models using symbolic knowledge bases, with a new operation for multi-hop template construction.
result Simple neural models achieve competitive performance on multi-hop reasoning tasks.
A new multi-hop FiLM approach improves visual reasoning tasks.
problem Challenging multi-modal tasks like visual question-answering and dialogue.
method Generate FiLM layer parameters in a multi-hop fashion, alternating between attending to language and generating parameters.
result Multi-hop FiLM generation achieves state-of-the-art performance on visual dialogue tasks.
Two-hop walks reveal PageRank order in networks.
problem Determining pairwise PageRank order in large networks.
method Two-hop walks and a sign-mirror function.
result High pairwise correct rate in PageRank order.
NEAR improves graph classification by aggregating edge information.
problem Loss of local structure and relationships in 1-hop neighborhood GNNs.
method Proposes NEAR, a framework that aggregates edge information between nodes in the neighborhood.
result NEAR improves graph classification tasks over existing 1-hop based GNN algorithms.
A novel beam training scheme optimizes multi-hop THz communications with up to 75% performance gain.
problem Optimizing beam training for multi-hop THz communications with high data rates and low time overhead.
method Developed a reinforcement learning-based hierarchical beam training scheme with dynamic training levels.
result The proposed scheme achieves up to 75% performance gain in spectral efficiency compared to conventional methods.
Study finds periodic orbits in a complex gravitational system.
problem Existence of periodic solutions in a gravitational system with multiple primaries.
method Proves existence of periodic solutions when primaries move on a Hip-Hop solution.
result Proves the existence of periodic solutions in the restricted ( 2 N + 1 ) (2N+1) ( 2 N + 1 ) -body problem. Method integrates logical rules into neural multi-hop reasoning for drug repurposing.
problem Capturing long-range dependencies in biomedical data.
method Combines logical rules with neural multi-hop reasoning using reinforcement learning.
result Our method outperforms baseline methods in drug repurposing tasks.
Hop Sampling improves GNNs in non-stationary environments by preventing overfitting.
problem Non-stationary environments cause concept drift, making GNNs overfit to training graphs.
method Randomly selects the number of propagation steps in GNNs to prevent overfitting.
result Improves GNNs' prediction accuracy by 7.97% and 16.93% in LINE Coupon recommender systems.
Empirical law predicts accuracy of Google Translate's translation chains.
problem Predicting accuracy in machine translation with multiple hops.
method Empirical testing of Google Translate's sequential translation.
result Accuracy decreases with the number of translating hops, following a power law.
New method uses multi-hop assortativity to classify network functionalities.
problem Classifying network functionalities based on structure and metadata.
method Introduces multi-hop assortativity to capture node similarity in paths.
result Multi-hop assortativity features outperform state-of-the-art methods in network classification.
Proposes a framework for private data augmentation in federated learning.
problem Privacy and performance issues in non-IID training datasets.
method Multi-hop federated augmentation with sample compression.
result Significantly improves privacy, transmission delay, and local training performance.
Improved bipartite link prediction using 2-hop paths.
problem Link prediction in bipartite networks without node attributes.
method Multiply reconstructed adjacency matrix with symmetrically normalized training adjacency matrix to form 2-hop paths.
result 2-hop paths improve link prediction performance.
Proposes HOPF framework for CC using higher-order propagation.
problem Collective Classification struggles with node information morphing across multiple hops.
method Iterative inference mechanism with differentiable kernels for multi-hop neighborhood information.
result NIP models preserve node information and provide more robust performance.
F-GCN improves graph convolutional networks for semi-supervised node classification.
problem Improving representation capacity of graph convolutional networks for multi-hop neighborhood information.
method Proposes a mathematically motivated, yet simple extension to existing GCNs.
result F-GCN outperforms state-of-the-art models on six out of eight datasets.
MAGNA improves graph neural networks by incorporating multi-hop context information.
problem Limited context in current graph neural networks.
method Diffuses attention scores across the network, accounting for all paths between nodes.
result State-of-the-art performance on node classification and knowledge graph completion benchmarks.
End-to-end KBQA system learns from multiple reasoning paths without labeled paths.
problem Lack of labeled reasoning paths limits KBQA system performance.
method End-to-end KBQA system using multiple reasoning paths.
result Demonstrates strong performance on various KBQA datasets.
To cope with the high level of ambiguity faced in domains such as Computer Vision or Natural Language processing, robust prediction methods often search for a diverse set of high-quality candidate solutions or proposals. In structured prediction problems, this becomes a daunting task, as the solution space (image label…
Indirect attacks can fool graph classifiers even with poisoned neighbors.
problem How to evaluate and defend graph convolutional neural networks against indirect adversarial attacks.
method Proposed a method to generate adversarial perturbations on a single node far from the target.
result 99% attack success rate within two-hops from the target in two datasets.
Knowledge base (KB) completion adds new facts to a KB by making inferences from existing facts, for example by inferring with high likelihood nationality(X,Y) from bornIn(X,Y). Most previous methods infer simple one-hop relational synonyms like this, or use as evidence a multi-hop relational path treated as an atomic f…
Unified routing and arbitrage with concave continuation.
problem Combining routing and arbitrage in financial markets.
method Extending AMM trade functions to negative inputs via concave continuation.
result Unified approach unifies routing and arbitrage.
Simpler linear models outperform complex GCN encoders for graph tasks.
problem Complex graph autoencoders and variational autoencoders.
method Replacing GCN encoders with one-hop linear models.
result Simpler linear models achieve competitive performance with fewer operations and parameters.
Adaptive computation improves machine reasoning for complex tasks.
problem Learning to perform multi-hop inference for complex tasks.
method Introduced a model with Adaptive Computation Time to learn the number of inference steps.
result Adaptive computation provides a small performance benefit and insight into reasoning.
Improved graph neural networks by separating feature aggregation and depth.
problem Understanding feature importance in graph neural networks without prior information.
method Decoupling feature aggregation and depth, using softmax as a regularizer, and introducing 'Soft-Selector' and 'Hop-Normalization'.
result FSGNN model achieves up to 64% accuracy improvements in node classification tasks.
Dual-attention GCN improves text classification by adapting to textual complexity.
problem Challenges in learning discriminative features from texts due to graph variants.
method Proposes a dual-attention GCN with connection-attention and hop-attention mechanisms.
result Achieves state-of-the-art performance on text classification tasks.
FinReflectKG benchmarks financial QA by linking relevant context from a financial KG, improving model performance and efficiency.
problem Efficiently retrieving and navigating relevant financial information across diverse sources and years.
method A benchmark built on a temporally indexed financial KG, generating QA pairs via pattern-specific prompts and quality control, evaluating retrieval scenarios.
result KG-guided retrieval yields substantial gains in correctness and token utilization, improving model performance by 24%.
GraphACL learns graph representations without augmentation or homophily assumptions.
problem Learning graph representations on heterophilic graphs (nodes with different labels and features).
method Asymmetric Contrastive Learning for Graphs (GraphACL) considers an asymmetric view of neighboring nodes.
result GraphACL significantly outperforms state-of-the-art methods on both homophilic and heterophilic graphs.
LNPE enhances local connections in embeddings using extended neighbor propagation.
problem Improving local connections and interactions in nonlinear dimensionality reduction.
method Inspired by GCN, LNPE extends 1-hop neighbors to n-hop neighbors in LLE.
result LNPE produces more faithful and robust embeddings with better topological and geometrical properties.
Superhighway bypasses data sparsity in cross-domain CF.
problem Data sparsity in cross-domain collaborative filtering.
method Explicit relation-enrichment procedure to enhance cross-domain connectivity.
result Significantly improves recommendation performance in both target and source domains.
New neural KB representation speeds up reasoning with large symbolic knowledge bases.
problem Efficiently reasoning with large symbolic knowledge bases.
method Sparse-matrix reified knowledge base, enabling fully differentiable, scalable neural modules.
result Competitive performance on KB completion and semantic parsing benchmarks.
Enhanced Hopfield model boosts memory retrieval capacity.
problem Memory retrieval in modern Hopfield models with limited capacity.
method Introduces a learnable feature map transforming energy function into kernel space, minimizing separation loss for uniform memory distribution.
result Significant reduction in metastable states, enhancing memory capacity and retrieval accuracy.
Graph neural networks improve volatility forecasting by capturing spillover effects.
problem Forecasting multivariate realized volatility with spillover effects.
method Customized graph neural networks incorporating spillover effects from multi-hop neighbors.
result Modeling nonlinear spillover effects enhances forecasting accuracy, especially for short-term horizons.
This work reveals symmetries in quantum circuits and develops a noise-aware optimization method.
problem Understanding and optimizing the cost landscape of parametrized quantum circuits.
method Analytical proof of symmetries and their resilience to noise, followed by the development of SYMH optimization method.
result Symmetries in PQCs lead to degeneracy in the cost landscape and can be exploited to improve optimization under noise.
Decentralized learning over graphs improves model accuracy.
problem Training machine learning models in a fully decentralized manner.
method Nodes aggregate information from one-hop neighbors to learn a model fitting the entire network.
result The proposed algorithm reduces error probability for every node in the network.
This study compares GNNs and GA-MLPs, finding GA-MLPs can distinguish graphs but not count walks.
problem Comparing expressive power and graph isomorphism testing capabilities of GNNs and GA-MLPs.
method GA-MLPs augment node features with multi-hop operators and apply MLPs node-wise; GNNs are compared as a baseline.
result GA-MLPs can distinguish almost all non-isomorphic graphs but cannot count attributed walks, unlike GNNs.
AWARE improves graph prediction by aggregating walks with attention schemes.
problem Improving graph prediction accuracy using walk aggregation.
method Integrates attention schemes into walk-aggregating GNNs.
result AWARE outperforms existing methods in graph-level prediction tasks.
Graph Cascades rewire graphs to improve structure-aware learning.
problem Improving graph neural networks and transformers for structure-aware learning.
method Graph Cascades uses contagion-based diffusion processes to construct an auxiliary graph with reinforced edges.
result Graph Cascades improves node-classification benchmarks across various graph types.
FairACE improves fairness in GNNs by balancing node performance across degree groups.
problem Degree biases in GNNs lead to unequal prediction performance among nodes with varying degrees.
method Integrates asymmetric contrastive learning with adversarial training to balance performance between high-degree and low-degree nodes.
result Significantly improves degree fairness metrics while maintaining competitive accuracy.
AdaGCN uses AdaBoost to efficiently integrate high-order neighbor knowledge in graph neural networks.
problem Efficiently exploring and exploiting knowledge from different hops of neighbors in graph neural networks.
method Incorporates AdaBoost into graph convolutional networks to integrate knowledge from high-order neighbors.
result AdaGCN achieves state-of-the-art prediction performance across different graphs and label rates.
Novel CG-EGNNs learn equivariant functions from Clifford algebras.
problem Lack of equivariance in high-order graph neural networks.
method Integrates high-order local structures with Clifford algebras for equivariant learning.
result CG-EGNNs outperform previous methods on various benchmarks.
TSDS framework reduces edge LLM agent compute by 43%-73% while maintaining safety and reliability.
problem Managing reasoning budget and uncertainty in edge LLM agents.
method Integrates a lightweight convergence probe and a perplexity-based deferral rule calibrated via multi-objective LTT.
result Reduces per-episode thinking compute by 43%-73% over deferral-only baselines.
This paper improves radar performance against jammers using RL.
problem Improving radar performance against jammers.
method Reinforcement Learning (RL) with Deep Q-Network (DQN) and Long Short Term Memory (LSTM) networks.
result Softmax operator improves RL algorithm performance.
Decentralized learning over social networks using Bayesian methods.
problem Training models on distributed data in a decentralized manner.
method Decentralized Bayesian learning algorithm over a graph, using peer-to-peer model aggregation.
result Systematic treatment of model aggregation over arbitrary connected graphs with strong analytic guarantees.