Arrow Research search

Author name cluster

Naoki Abe

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers
2 author rows

Possible papers

15

ICML Conference 2025 Conference Paper

ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks

  • Saurabh Jha
  • Rohan R. Arora
  • Yuji Watanabe
  • Takumi Yanagawa
  • Yinfang Chen
  • Jackson Clark
  • Bhavya
  • Mudit Verma

Realizing the vision of using AI agents to automate critical IT tasks depends on the ability to measure and understand effectiveness of proposed solutions. We introduce ITBench, a framework that offers a systematic methodology for benchmarking AI agents to address real-world IT automation tasks. Our initial release targets three key areas: Site Reliability Engineering (SRE), Compliance and Security Operations (CISO), and Financial Operations (FinOps). The design enables AI researchers to understand the challenges and opportunities of AI agents for IT automation with push-button workflows and interpretable metrics. IT-Bench includes an initial set of 102 real-world scenarios, which can be easily extended by community contributions. Our results show that agents powered by state-of-the-art models resolve only 11. 4% of SRE scenarios, 25. 2% of CISO scenarios, and 25. 8% of FinOps scenarios (excluding anomaly detection). For FinOps-specific anomaly detection (AD) scenarios, AI agents achieve an F1 score of 0. 35. We expect ITBench to be a key enabler of AI-driven IT automation that is correct, safe, and fast. IT-Bench, along with a leaderboard and sample agent implementations, is available at https: //github. com/ibm/itbench.

Details

TMLR Journal 2024 Journal Article

Directed Graph Transformers

  • Qitong Wang
  • Georgios Kollias
  • Vasileios Kalantzis
  • Naoki Abe
  • Mohammed J Zaki

In this paper, we address the problem of capturing graph directionality using transformers. Most existing graph transformers typically capture distances between graph nodes and do not take edge direction into account. This is a limiting assumption since many graph applications need to exploit sophisticated relationships in graph data, such as time, causality, or generic dependency constraints. We introduce a novel graph transformer architecture that explicitly takes into account the directionality between connected graph nodes. To achieve this, we make use of dual encodings to represent both potential roles, i.e., source or target, of each pair of vertices linked by a directed edge. These encodings are learned by leveraging the latent adjacency information extracted from a directional attention module, localized with $k$-hop neighborhood information. Extensive experiments on synthetic and real graph datasets show that our approach can have significant accuracy gains over previous graph transformer (GT) and graph neural network (GNN) approaches, providing state-of-the-art (SOTA) results on inherently directed graphs.

PDF Details

AAAI Conference 2022 Conference Paper

Directed Graph Auto-Encoders

  • Georgios Kollias
  • Vasileios Kalantzis
  • Tsuyoshi Ide
  • Aurélie Lozano
  • Naoki Abe

We introduce a new class of auto-encoders for directed graphs, motivated by a direct extension of the Weisfeiler-Leman algorithm to pairs of node labels. The proposed model learns pairs of interpretable latent representations for the nodes of directed graphs, and uses parameterized graph convolutional network (GCN) layers for its encoder and an asymmetric inner product decoder. Parameters in the encoder control the weighting of representations exchanged between neighboring nodes. We demonstrate the ability of the proposed model to learn meaningful latent embeddings and achieve superior performance on the directed link prediction task on several popular network datasets.

PDF Details

AAAI Conference 2021 Conference Paper

Anomaly Attribution with Likelihood Compensation

  • Tsuyoshi Idé
  • Amit Dhurandhar
  • Jiří Navrátil
  • Moninder Singh
  • Naoki Abe

This paper addresses the task of explaining anomalous predictions of a black-box regression model. When using a black-box model, such as one to predict building energy consumption from many sensor measurements, we often have a situation where some observed samples may significantly deviate from their prediction. It may be due to a sub-optimal black-box model, or simply because those samples are outliers. In either case, one would ideally want to compute a “responsibility score” indicative of the extent to which an input variable is responsible for the anomalous output. In this work, we formalize this task as a statistical inverse problem: Given model deviation from the expected value, infer the responsibility score of each of the input variables. We propose a new method called likelihood compensation (LC), which is founded on the likelihood principle and computes a correction to each input variable. To the best of our knowledge, this is the first principled framework that computes a responsibility score for real valued anomalous model deviations. We apply our approach to a real-world building energy prediction task and confirm its utility based on expert feedback.

PDF Details

NeurIPS Conference 2021 Conference Paper

Cardinality-Regularized Hawkes-Granger Model

  • Tsuyoshi Ide
  • Georgios Kollias
  • Dzung Phan
  • Naoki Abe

We propose a new sparse Granger-causal learning framework for temporal event data. We focus on a specific class of point processes called the Hawkes process. We begin by pointing out that most of the existing sparse causal learning algorithms for the Hawkes process suffer from a singularity in maximum likelihood estimation. As a result, their sparse solutions can appear only as numerical artifacts. In this paper, we propose a mathematically well-defined sparse causal learning framework based on a cardinality-regularized Hawkes process, which remedies the pathological issues of existing approaches. We leverage the proposed algorithm for the task of instance-wise causal event analysis, where sparsity plays a critical role. We validate the proposed framework with two real use-cases, one from the power grid and the other from the cloud data center management domain.

PDF Details

NeurIPS Conference 2009 Conference Paper

Grouped Orthogonal Matching Pursuit for Variable Selection and Prediction

  • Grzegorz Swirszcz
  • Naoki Abe
  • Aurelie Lozano

We consider the problem of variable group selection for least squares regression, namely, that of selecting groups of variables for best regression performance, leveraging and adhering to a natural grouping structure within the explanatory variables. We show that this problem can be efficiently addressed by using a certain greedy style algorithm. More precisely, we propose the Group Orthogonal Matching Pursuit algorithm (Group-OMP), which extends the standard OMP procedure (also referred to as ``forward greedy feature selection algorithm for least squares regression) to perform stage-wise group variable selection. We prove that under certain conditions Group-OMP can identify the correct (groups of) variables. We also provide an upperbound on the $l_\infty$ norm of the difference between the estimated regression coefficients and the true coefficients. Experimental results on simulated and real world datasets indicate that Group-OMP compares favorably to Group Lasso, OMP and Lasso, both in terms of variable selection and prediction accuracy.

PDF Details

TCS Journal 1995 Journal Article

Exact learning of linear combinations of monotone terms from function value queries

  • Atsuyoshi Nakamura
  • Naoki Abe

We investigate the problem of exactly identifying a real-valued function of {0, 1} n represented by a weighted sum of a number of monotone terms by querying for the values of the target function at assignments of the learner's choice. When all coefficients are nonnegative, we exhibit an efficient learning algorithm requiring at most (n − ⌊log s⌋ + 1)s queries, where n is the number of variables and s is the number of terms in the target formula. We prove a lower bound of Ω( ns log s ) on the number of queries necessary for learning this class, so no algorithm can reduce the number of queries dramatically. The algorithm runs in time O(ns 2) in the worst case. The same algorithm can be used to learn the ‘inductive-read-k’ subclass, a proper super class of the ‘read-k’ subclass, with a number of queries not exceeding 1 2 ((n − ⌊log k⌋)(n − ⌊log k⌋ + 1) + 2)k, which improves upon the bound achievable by a naive learning algorithm by a factor of two. In addition, the above method can be extended to handle the nonmonotone case in some restricted sense: A similar algorithm can learn the unate linear combinations of terms with a comparable number of queries. In the general case, namely, when the coefficients vary over the reals (or any arbitrary field), we show that the number of queries required for exact learning of the k-term subclass is upper bounded by q(n, ⌊log k⌋ + 1) and is lower bounded by q(n, ⌊log k⌋), where q(n, l) = ∑l i = 0 (n i). These bounds are shown by generalizing Roth and Benedek's technique for analyzing the learning problem for k-sparse multivariate polynomials over GF(2) (Roth and Benedek, 1991) to those over an arbitrary field.

Details DOI
v2026.09.13