GrAPL identifies arms above a threshold using graph similarity.
problem Efficiently identifying arms with means above a threshold in a graph-structured bandit problem.
method Thresholding Graph Bandits with GrAPL algorithm exploiting graph structure and reward homophily.
result GrAPL effectively identifies arms above a threshold using graph structure and reward homophily.
Novel method HAO mitigates Graph Injection Attack by preserving homophily.
problem Graph Injection Attack's high flexibility can harm graph homophily.
method Introduce homophily unnoticeability constraint and Harmonious Adversarial Objective (HAO).
result GIA with HAO breaks homophily-based defenses and outperforms previous attacks.
A new GNN framework for graphs with heterophily.
problem Graphs with heterophily (nodes from different classes often connected).
method CPGNN framework with an interpretable compatibility matrix.
result CPGNN achieves state-of-the-art results in heterophily settings.
MPNNs struggle with class-bottlenecks and heterophily, leading to performance limitations.
problem Performance limitations of MPNNs under heterophily and structural bottlenecks.
method A statistical framework decomposing model performance into SNR components and proving bounds on sensitivity.
result Optimal graph structures for maximizing higher-order homophily are disjoint unions of single-class and two-class-bipartite clusters.
Graph neural networks struggle with heterophily, but new designs improve their performance.
problem Graph neural networks struggle with heterophily (networks where connected nodes may have different class labels and dissimilar features).
method Ego- and neighbor-embedding separation, higher-order neighborhoods, and combination of intermediate representations.
result The identified designs increase the accuracy of GNNs by up to 40% and 27% over models without them on synthetic and real networks with heterophily, respectively.
Unified framework for multi-user bandits using Laplacian kernels.
problem Multi-user contextual bandits with graph-related users and non-linear rewards.
method Joint penalty combining graph smoothness and individual roughness in a unified RKHS.
result Unified multi-user RKHS and effective dimension for regret bounds.
GCNs perform well on heterophilous graphs under certain conditions.
problem The necessity of homophily for good GNN performance.
method Empirical evaluation and theoretical analysis of GCNs on heterophilous graphs.
result GCNs can achieve strong performance on heterophilous graphs under certain conditions.
GCNs help in diagnosing label scarcity and feature quality on graphs.
problem Understanding when GCNs improve node classification.
method Simulated label scarcity, feature ablation, and per-class analysis.
result GCNs provide largest gains under extreme label scarcity, matching original performance with noisy features, but hurt when homophily is low and features are strong.
New spectral clustering method handles discrete covariates for better community detection.
problem Community detection in networks with discrete covariates.
method Spectral algorithm that separates latent network structure from observed covariates.
result Achieves perfect clustering with high probability in large, sparse networks.
Model distinguishes homophily and triadic closure in network analysis.
problem Conflated properties of homophily and transitivity in network analysis.
method Generative model with triadic closure edges and inference procedure.
result Can identify mechanisms responsible for network edges and community structure.
Study finds corporate boards with women appoint more women, leading to better profitability.
problem Influence of female board members on corporate profitability.
method Analysis of Japanese corporate boards and their interlocks.
result Corporate boards with women appoint more women, leading to higher profitability.
Study shows peers' graduation improves residents' success in TCs.
problem Identifying peer influence in therapeutic communities adjusting for latent homophily.
method Used data on affirmations and exit dates to form peer networks, modeled latent homophily, and proposed bias correction methods.
result Positive effect of peers' graduation on residents' graduation, varying by gender, race, and role model definition.
New framework analyzes belief evolution in social networks.
problem Analyzing belief evolution in social networks.
method Proposes a new theoretical framework using Markov chain theory for horizontal and vertical transmission.
result Homophily-based networks do not converge to a single set of beliefs.
SCNode improves node embeddings for GNNs in both homophilic and heterophilic graphs.
problem Challenges in node representation quality and generalization in GNNs, especially in heterophilic graphs.
method SCNode integrates spatial and contextual information to create more discriminative and structurally aware node embeddings.
result SCNode achieves superior performance over conventional GNN models on benchmark datasets.
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.
FairDrop improves fairness in graph representation learning by counteracting homophily.
problem Ensuring fairness in graph representation learning, especially in scenarios with protected attributes.
method Proposes a biased edge dropout algorithm (FairDrop) to counteract homophily and improve fairness.
result Successfully improves fairness in all models up to a small or negligible drop in accuracy.
Many widely studied graphical models with latent variables lead to nontrivial constraints on the distribution of the observed variables. Inspired by the Bell inequalities in quantum mechanics, we refer to any linear inequality whose violation rules out some latent variable model as a "hidden variable test" for that mod…
Estimates peer influence effects using embeddings for social networks.
problem Estimating peer contagion effects in social networks with unobserved confounders.
method Nonparametrically adjusts for homophily using node embeddings.
result Formalizes causal effect of peer influence in social networks.
GCNs learn by embedding similar nodes within a class and leveraging consistent neighborhood structures.
problem Understanding how GCNs perform semi-supervised node classification on both homophilous and heterophilous graphs.
method Investigated the latent node embeddings and neighborhood structures of GCNs.
result GCNs learn by embedding similar nodes within a class and leveraging consistent neighborhood structures.
Rewiring GNNs to optimize community and feature alignment improves their performance.
problem Improving GNNs' performance by addressing over-squashing and generalization issues.
method Three rewiring strategies: ComMa, FeaSt, and ComFy, targeting community structure, node labels, and their alignment.
result Rewiring strategies enhance GNNs' performance by optimizing label-community alignment.
Improved graph attention model for noisy graphs.
problem Understanding and improving graph attention in noisy graphs.
method Proposes SuperGAT, a self-supervised graph attention network.
result SuperGAT learns more expressive attention by encoding edges.
ECGs improve GNNs for non-homophilic data.
problem Improving GNNs for datasets where nodes are not likely to belong to the same class.
method ECGs rewire GNNs' computation graph to connect nodes likely in the same class using weaker classifiers.
result ECGs improve GNN performance on non-homophilic datasets.
GNNs generalize better on homophilic graphs than heterophilic ones.
problem Understanding the generalization error of GNNs on graph data.
method Analytical tools from statistical physics and random matrix theory.
result Risk is shaped by graph noise, feature noise, and training labels.
Heterophily affects GNN robustness; separating ego- and neighbor-embeddings improves defense.
problem The robustness of GNNs to adversarial attacks.
method Formalized relation between heterophily and GNN robustness; empirical analysis; design principles for improved robustness.
result Separating ego- and neighbor-embeddings increases GNN robustness.
New non-homophilous graph datasets and methods for scalable learning.
problem Evaluation of graph learning methods on non-homophilous graphs.
method Introducing LINKX, a simple yet strong method for scalable non-homophilous graph learning.
result LINKX achieves state-of-the-art performance on non-homophilous graphs.
Model shows how diversity on corporate boards influences decision-making and innovation.
problem Understanding dynamics of diversity and innovation in corporate boards.
method Developed a dynamic model calibrated with empirical data of firm and board networks.
result Homophily and visibility biases shape the trajectory towards equality in corporate boards.
New method reveals why GNNs perform well on certain datasets.
problem Understanding why GNNs perform differently on similar datasets.
method Deriving exact generalization error for various GNN architectures.
result Benchmark datasets favor architectures that rely on graph structure.
Adaptive GPR-GNN optimizes node feature and topology learning.
problem Optimizing GNNs for both node features and graph topology, regardless of homophily or heterophily.
method Adaptive Universal Generalized PageRank (GPR) Graph Neural Network (GPR-GNN) that learns optimal GPR weights.
result Significant performance improvement on node classification tasks compared to state-of-the-art GNNs.
ES-MLP combines Graph-MLP with edge splitting for node classification on both homophilic and heterophilic graphs.
problem Node classification on graphs with mixed homophilic and heterophilic properties.
method Combines Graph-MLP with edge splitting mechanism from ES-GNN to learn two adjacency matrices based on relevant and irrelevant feature pairs.
result ES-MLP achieves performance comparable to homophilic and heterophilic models without using edges during inference.
A hierarchical gamma process infinite edge partition model is proposed to factorize the binary adjacency matrix of an unweighted undirected relational network under a Bernoulli-Poisson link. The model describes both homophily and stochastic equivalence, and is scalable to big sparse networks by focusing its computation…
We analyze the information-theoretic limits for the recovery of node labels in several network models. This includes the Stochastic Block Model, the Exponential Random Graph Model, the Latent Space Model, the Directed Preferential Attachment Model, and the Directed Small-world Model. For the Stochastic Block Model, the…
Paper proposes JDR to denoise graph features and rewire graphs for better node classification.
problem Jointly denoise noisy graph features and rewire graphs for improved node classification.
method Align leading spectral spaces of graph and feature matrices to solve non-convex optimization problem.
result JDR consistently outperforms existing methods on various node classification tasks.
Network embedding algorithms are able to learn latent feature representations of nodes, transforming networks into lower dimensional vector representations. Typical key applications, which have effectively been addressed using network embeddings, include link prediction, multilabel classification and community detectio…
Reward hacking exploits misspecified rewards, affecting agent capabilities and true performance.
problem Reward hacking in RL models exploiting reward misspecifications.
method Constructed four RL environments with misspecified rewards; analyzed agent capabilities and behavior.
result More capable agents exploit reward misspecifications, achieving higher proxy reward but lower true reward.
Generative model controls heterophily in graph signals.
problem Controlling heterophily in graph signals for better model effectiveness.
method Combines graphon-based generator with spectral filtering of Gaussian node features.
result Establishes theoretical guarantees for heterophily control and convergence.
Paper introduces PRMs to learn non-Markovian stochastic rewards for reinforcement learning.
problem Lack of structured representation for non-Markovian stochastic rewards in reinforcement learning.
method Introduces probabilistic reward machines (PRMs) and presents an algorithm to learn them from decision processes.
result Algorithm proves correct and convergent for learning PRMs from decision processes.
Paper addresses reward learning issues in RL, improving both under- and over-estimation.
problem Reward learning from data can lead to reward delusions or underestimation, causing unintended behaviors.
method Connects reward learning to positive-unlabeled (PU) learning and applies a large-scale PU learning algorithm.
result Improves both GAIL and supervised reward learning without additional assumptions.
This work analyzes the value of future reward information in RL.
problem Analyzing the impact of knowing future rewards in reinforcement learning.
method Competitive analysis and worst-case reward distribution.
result Exact ratios between standard RL agents and those with future-reward lookahead.
Self-supervised reward prediction improves RL in sparse reward settings.
problem Data efficiency and sparse reward signals in reinforcement learning.
method Learning a state representation for reward prediction and using it to shape rewards.
result Self-supervised reward prediction enhances RL algorithms in single-goal environments.
The study categorizes reward errors in reinforcement learning, finding some can be beneficial.
problem Training language models with imperfect proxy rewards.
method Theoretical analysis of policy gradient optimization and categorization of reward errors.
result Reward errors can be benign or even beneficial, preventing policy from stalling.
Reward collapse occurs when ranking-based reward models yield uniform rewards for different prompts.
problem Reward collapse in aligning large language models with human preferences.
method Introduced a prompt-aware optimization scheme to derive closed-form expressions for reward distributions.
result Our prompt-aware utility functions significantly alleviate reward collapse during training.
Reward models need more than just accuracy for effective RLHF.
problem The effectiveness of reward models in RLHF is not fully understood.
method An optimization perspective to evaluate reward models.
result Reward models with low reward variance can lead to a flat optimization landscape, hindering performance.
Proposes a method to boost deep reinforcement learning with sparse rewards.
problem Challenges in learning complex behaviors with long horizons and sparse rewards.
method Predictive coding for reward shaping.
result Achieves better learning by providing reward signals that understand environment dynamics and emphasize useful features.
Action guidance helps agents learn true objectives in games with sparse rewards.
problem Training agents in games with sparse rewards requires significant exploration.
method Action guidance, a novel technique that combines exploration with reward shaping.
result Action guidance enables agents to optimize true objectives efficiently.
New RL method uses distance between states instead of rewards for sparse reward environments.
problem Sparse rewards or non-reward environments in reinforcement learning.
method Uses goal-distance gradient and bridge point planning for policy improvement.
result Significantly better performance on sparse reward and local optimal problems in complex environments.
Paper proposes RRD to learn proxy rewards for sparse delayed rewards in episodic reinforcement learning.
problem Learning from sparse and delayed rewards in reinforcement learning.
method Randomized Return Decomposition (RRD) algorithm to redistribute rewards.
result Substantial improvement over baseline algorithms in experiments.
Enhances reward specification in RL with a novel language-based approach.
problem Reward specification in RL can lead to unintended, potentially harmful behaviours.
method Developed a novel class of language-based Reward Machines using RML's built-in memory.
result Can specify non-regular, non-Markovian reward functions for complex tasks.
Reward tweaking optimizes behavior for long-term goals by adjusting the reward function.
problem Optimizing behavior for long-term goals in reinforcement learning with unstable long planning horizons.
method Reward tweaking learns a surrogate reward function that induces optimal behavior for the original task.
result Reward tweaking guides agents towards better long-term returns while planning for short horizons.