arXiv subjects

Takanori Maehara

Publications and source records attributed to Takanori Maehara.

At least 19 recordsLinked to original sources

arXiv2026

Distinguishing graphs with simple spectrum by homomorphism counts

We study which graph classes determine every graph with simple spectrum up to isomorphism by homomorphism counts from their members. We show that such a class has unbounded treewidth and Euler genus and contains a graph with the complete graph on seven vertices as a minor. To prove these conditions, we construct pairs of non-isomorphic cospectral graphs with simple spectrum, each bipartite, nonsingular and of maximum degree at most six. The construction attaches rooted trees to Cai-Furer-Immerman graphs and preserves homomorphism indistinguishability over every minor-closed class. We then prove that subcubic homomorphism counts determine every graph whose adjacency matrix has kernel dimension at most one. This extends the known result for nonsingular graphs and applies to all graphs with simple spectrum. We also prove that two graphs have the same subcubic homomorphism counts if and only if they have the same number of vertices and there is a bijective linear isometry between the images of their adjacency matrices that intertwines the adjacency operators and preserves the coordinatewise trilinear forms. Finally, we prove that homomorphism counts from the single-vertex graph and from subdivisions of any sequence of connected cubic graphs have the same distinguishing power as subcubic homomorphism counts if every complete graph is a minor of some member of the sequence.

math.CO↗

arXiv2023

Self-Supervised Pretraining for Heterogeneous Hypergraph Neural Networks

Recently, pretraining methods for the Graph Neural Networks (GNNs) have been successful at learning effective representations from unlabeled graph data. However, most of these methods rely on pairwise relations in the graph and do not capture the underling higher-order relations between entities. Hypergraphs are versatile and expressive structures that can effectively model higher-order relationships among entities in the data. Despite the efforts to adapt GNNs to hypergraphs (HyperGNN), there are currently no fully self-supervised pretraining methods for HyperGNN on heterogeneous hypergraphs. In this paper, we present SPHH, a novel self-supervised pretraining framework for heterogeneous HyperGNNs. Our method is able to effectively capture higher-order relations among entities in the data in a self-supervised manner. SPHH is consist of two self-supervised pretraining tasks that aim to simultaneously learn both local and global representations of the entities in the hypergraph by using informative representations derived from the hypergraph structure. Overall, our work presents a significant advancement in the field of self-supervised pretraining of HyperGNNs, and has the potential to improve the performance of various graph-based downstream tasks such as node classification and link prediction tasks which are mapped to hypergraph configuration. Our experiments on two real-world benchmarks using four different HyperGNN models show that our proposed SPHH framework consistently outperforms state-of-the-art baselines in various downstream tasks. The results demonstrate that SPHH is able to improve the performance of various HyperGNN models in various downstream tasks, regardless of their architecture or complexity, which highlights the robustness of our framework.

cs.LG↗

arXiv2021

Learning on Random Balls is Sufficient for Estimating (Some) Graph Parameters

Theoretical analyses for graph learning methods often assume a complete observation of the input graph. Such an assumption might not be useful for handling any-size graphs due to the scalability issues in practice. In this work, we develop a theoretical framework for graph classification problems in the partial observation setting (i.e., subgraph samplings). Equipped with insights from graph limit theory, we propose a new graph classification model that works on a randomly sampled subgraph and a novel topology to characterize the representability of the model. Our theoretical framework contributes a theoretical validation of mini-batch learning on graphs and leads to new learning-theoretic results on generalization bounds as well as size-generalizability without assumptions on the input.

cs.LG↗

arXiv2021

Abelian Neural Networks

We study the problem of modeling a binary operation that satisfies some algebraic requirements. We first construct a neural network architecture for Abelian group operations and derive a universal approximation property. Then, we extend it to Abelian semigroup operations using the characterization of associative symmetric polynomials. Both models take advantage of the analytic invertibility of invertible neural networks. For each case, by repeating the binary operations, we can represent a function for multiset input thanks to the algebraic structure. Naturally, our multiset architecture has size-generalization ability, which has not been obtained in existing methods. Further, we present modeling the Abelian group operation itself is useful in a word analogy task. We train our models over fixed word embeddings and demonstrate improved performance over the original word2vec and another naive learning method.

cs.LG↗

arXiv2020

r-Gathering Problems on Spiders:Hardness, FPT Algorithms, and PTASes

We consider the min-max $r$-gathering problem described as follows: We are given a set of users and facilities in a metric space. We open some of the facilities and assign each user to an opened facility such that each facility has at least $r$ users. The goal is to minimize the maximum distance between the users and the assigned facility. We also consider the min-max $r$-gather clustering problem, which is a special case of the $r$-gathering problem in which the facilities are located everywhere. In this paper, we study the tractability and the hardness when the underlying metric space is a spider, which answers the open question posed by Ahmed et al. [WALCOM'19]. First, we show that the problems are NP-hard even if the underlying space is a spider. Then, we propose FPT algorithms parameterized by the degree $d$ of the center. This improves the previous algorithms because they are parameterized by both $r$ and $d$. Finally, we propose PTASes to the problems. These are best possible because there are no FPTASes unless P=NP.

cs.DS↗

arXiv2020

Stacked Graph Filter

We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully connected weights versus trainable polynomial coefficients. We find that by stacking graph filters with learnable polynomial parameters, we can build a highly adaptive and robust vertex classification model. Our treatment here relaxes the low-frequency (or equivalently, high homophily) assumptions in existing vertex classification models, resulting a more ubiquitous solution in terms of spectral properties. Empirically, by using only one hyper-parameter setting, our model achieves strong results on most benchmark datasets across the frequency spectrum.

cs.LG↗

arXiv2020

Rank axiom of modular supermatroids: A connection with directional DR submodular functions

A matroid has been one of the most important combinatorial structures since it was introduced by Whitney as an abstraction of linear independence. As an important property of a matroid, it can be characterized by several different (but equivalent) axioms, such as the augmentation, the base exchange, or the rank axiom. A supermatroid is a generalization of a matroid defined on lattices. Here, the central question is whether a supermatroid can be characterized by several equivalent axioms similar to a matroid. Barnabei, Nicoletti, and Pezzoli characterized supermatroids on distributive lattices, and Fujishige, Koshevoy, and Sano generalized the results for cg-matroids (supermatroids on lower locally distributive lattices). In this study, we focus on modular lattices, which are an important superclass of distributive lattices, and provide equivalent characterizations of supermatroids on modular lattices. We characterize supermatroids on modular lattices using the rank axiom in which the rank function is a directional DR-submodular function, which is a generalization of a submodular function introduced by the authors. Using a characterization based on rank functions, we further prove the strong exchange property of a supermatroid, which has application in optimization. We also reveal the relation between the axioms of a supermatroid on lower semimodular lattices, which is a common superclass of a lower locally distributive lattice and a modular lattice.

math.CO↗

arXiv2020

Graph Homomorphism Convolution

In this paper, we study the graph classification problem from the graph homomorphism perspective. We consider the homomorphisms from $F$ to $G$, where $G$ is a graph of interest (e.g. molecules or social networks) and $F$ belongs to some family of graphs (e.g. paths or non-isomorphic trees). We show that graph homomorphism numbers provide a natural invariant (isomorphism invariant and $\mathcal{F}$-invariant) embedding maps which can be used for graph classification. Viewing the expressive power of a graph classifier by the $\mathcal{F}$-indistinguishable concept, we prove the universality property of graph homomorphism vectors in approximating $\mathcal{F}$-invariant functions. In practice, by choosing $\mathcal{F}$ whose elements have bounded tree-width, we show that the homomorphism method is efficient compared with other methods.

cs.LG↗

arXiv2020

Stochastic Monotone Submodular Maximization with Queries

We study a stochastic variant of monotone submodular maximization problem as follows. We are given a monotone submodular function as an objective function and a feasible domain defined on a finite set, and our goal is to find a feasible solution that maximizes the objective function. A special part of the problem is that each element in the finite set has a random hidden state, active or inactive, only the active elements contribute to the objective value, and we can conduct a query to an element to reveal its hidden state. The goal is to obtain a feasible solution having a large objective value by conducting a small number of queries. This is the first attempt to consider nonlinear objective functions in such a stochastic model. We prove that the problem admits a good query strategy if the feasible domain has a uniform exchange property. This result generalizes Blum et al.'s result on the unweighted matching problem and Behnezhad and Reyhani's result on the weighted matching problem in both objective function and feasible domain.

cs.DS↗

arXiv2020

Tightly Robust Optimization via Empirical Domain Reduction

Data-driven decision-making is performed by solving a parameterized optimization problem, and the optimal decision is given by an optimal solution for unknown true parameters. We often need a solution that satisfies true constraints even though these are unknown. Robust optimization is employed to obtain such a solution, where the uncertainty of the parameter is represented by an ellipsoid, and the scale of robustness is controlled by a coefficient. In this study, we propose an algorithm to determine the scale such that the solution has a good objective value and satisfies the true constraints with a given confidence probability. Under some regularity conditions, the scale obtained by our algorithm is asymptotically $O(1/\sqrt{n})$, whereas the scale obtained by a standard approach is $O(\sqrt{d/n})$. This means that our algorithm is less affected by the dimensionality of the parameters.

math.OC↗

arXiv2020

Learning Directly from Grammar Compressed Text

Neural networks using numerous text data have been successfully applied to a variety of tasks. While massive text data is usually compressed using techniques such as grammar compression, almost all of the previous machine learning methods assume already decompressed sequence data as their input. In this paper, we propose a method to directly apply neural sequence models to text data compressed with grammar compression algorithms without decompression. To encode the unique symbols that appear in compression rules, we introduce composer modules to incrementally encode the symbols into vector representations. Through experiments on real datasets, we empirically showed that the proposal model can achieve both memory and computational efficiency while maintaining moderate performance.

stat.ML↗

arXiv2019

Faking Fairness via Stealthily Biased Sampling

Auditing fairness of decision-makers is now in high demand. To respond to this social demand, several fairness auditing tools have been developed. The focus of this study is to raise an awareness of the risk of malicious decision-makers who fake fairness by abusing the auditing tools and thereby deceiving the social communities. The question is whether such a fraud of the decision-maker is detectable so that the society can avoid the risk of fake fairness. In this study, we answer this question negatively. We specifically put our focus on a situation where the decision-maker publishes a benchmark dataset as the evidence of his/her fairness and attempts to deceive a person who uses an auditing tool that computes a fairness metric. To assess the (un)detectability of the fraud, we explicitly construct an algorithm, the stealthily biased sampling, that can deliberately construct an evil benchmark dataset via subsampling. We show that the fraud made by the stealthily based sampling is indeed difficult to detect both theoretically and empirically.

stat.ML↗

arXiv2019

State-Space Based Network Topology Identification

In this work, we explore the state-space formulation of network processes to recover the underlying structure of the network (local connections). To do so, we employ subspace techniques borrowed from system identification literature and extend them to the network topology inference problem. This approach provides a unified view of the traditional network control theory and signal processing on networks. In addition, it provides theoretical guarantees for the recovery of the topological structure of a deterministic linear dynamical system from input-output observations even though the input and state evolution networks can be different.

eess.SP↗

arXiv2019

A Simple Proof of the Universality of Invariant/Equivariant Graph Neural Networks

We present a simple proof for the universality of invariant and equivariant tensorized graph neural networks. Our approach considers a restricted intermediate hypothetical model named Graph Homomorphism Model to reach the universality conclusions including an open case for higher-order output. We find that our proposed technique not only leads to simple proofs of the universality properties but also gives a natural explanation for the tensorization of the previously studied models. Finally, we give some remarks on the connection between our model and the continuous representation of graphs.

cs.LG↗

arXiv2019

Empirical Hypothesis Space Reduction

Selecting appropriate regularization coefficients is critical to performance with respect to regularized empirical risk minimization problems. Existing theoretical approaches attempt to determine the coefficients in order for regularized empirical objectives to be upper-bounds of true objectives, uniformly over a hypothesis space. Such an approach is, however, known to be over-conservative, especially in high-dimensional settings with large hypothesis space. In fact, an existing generalization error bound in variance-based regularization is $O(\sqrt{d \log n/n})$, where $d$ is the dimension of hypothesis space, and thus the number of samples required for convergence linearly increases with respect to $d$. This paper proposes an algorithm that calculates regularization coefficient, one which results in faster convergence of generalization error $O(\sqrt{\log n/n})$ and whose leading term is independent of the dimension $d$. This faster convergence without dependence on the size of the hypothesis space is achieved by means of empirical hypothesis space reduction, which, with high probability, successfully reduces a hypothesis space without losing the true optimum solution. Calculation of uniform upper bounds over reduced spaces, then, enables acceleration of the convergence of generalization error.

cs.LG↗

arXiv2019

PTAS and Exact Algorithms for $r$-Gathering Problems on Tree

r-gathering problem is a variant of facility location problems. In this problem, we are given a set of users and a set of facilities on same metric space. We open some of the facilities and assign each user to an open facility, so that at least r users are assigned to every open facility. We aim to minimize the maximum distance between user and assigned facility. In general, this problem is NP-hard and admit an approximation algorithm with factor 3. It is known that the problem does not admit any approximation algorithm within a factor less than 3. In our another paper, we proved that this problem is NP-hard even on spider, which is a special case of tree metric. In this paper, we concentrate on the problems on a tree. First, we give a PTAS for r-gathering problem on a tree. Furthermore, we give PTAS for some variants of the problems on a tree, and also give exact polynomial-time algorithms for another variants of r-gathering problem on a tree.

cs.DS↗

arXiv2019

$r$-Gather Clustering and $r$-Gathering on Spider: FPT Algorithms and Hardness

We consider min-max $r$-gather clustering problem and min-max $r$-gathering problem. In the min-max $r$-gather clustering problem, we are given a set of users and divide them into clusters with size at least $r$; the goal is to minimize the maximum diameter of clusters. In the min-max $r$-gathering problem, we are additionally given a set of facilities and assign each cluster to a facility; the goal is to minimize the maximum distance between the users and the assigned facility. In this study, we consider the case that the users and facilities are located on a ``spider'' and propose the first fixed-parameter tractable (FPT) algorithms for both problems, which are parametrized by only the number of legs. Furthermore, we prove that these problems are NP-hard when the number of legs is arbitrarily large.

cs.DS↗

arXiv2019

Multiple Knapsack-Constrained Monotone DR-Submodular Maximization on Distributive Lattice --- Continuous Greedy Algorithm on Median Complex ---

We consider a problem of maximizing a monotone DR-submodular function under multiple order-consistent knapsack constraints on a distributive lattice. Since a distributive lattice is used to represent a dependency constraint, the problem can represent a dependency constrained version of a submodular maximization problem on a set. We propose a $1 - 1/e$ approximation algorithm for this problem. To achieve this result, we generalize the continuous greedy algorithm to distributive lattices: We choose a median complex as a continuous relaxation of a distributive lattice and define the multilinear extension on it. We show that the median complex admits special curves, named uniform linear motions, such that the multilinear extension of a DR-submodular function is concave along a positive uniform linear motion, which is a key property of the continuous greedy algorithm.

cs.DS↗