Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 13351-13355· 0 citations· 25 references
Abstract
Foundation models are increasingly deployed as agentic data-and-memory systems built on pretrained parameters, retrieval corpora, external knowledge stores, and persistent interaction histories. For the Knowledge Discovery and Data Mining (KDD) community, this matters because recommendation, search, temporal modeling, enterprise knowledge systems, and AI for science are tasked with organizing long-tail, hierarchical, and relational data while supporting retrieval, adaptation, and memory at scale. Yet Euclidean latent spaces can be a limited fit for tree-like or ontology-rich structure. Hyperbolic geometry offers a useful modeling tool: its exponential volume growth supports compact representations of hierarchy, association, and asymmetric neighborhoods. This lecture-style tutorial covers hyperbolic methods for data organization, retrieval, and memory layers in foundation-model systems: manifold operations, scalable neural primitives, retrieval-aware pipelines, recommendation and knowledge systems, agent memory, multimodal and scientific data modeling, and lifecycle operations including fine-tuning, editing, and unlearning. We emphasize when curved geometry can improve KDD systems and how to evaluate and deploy those gains responsibly. Homepage: https://hyperboliclearning.github.io/events/kdd2026tutorial.
Large language models (LLMs) have transformed AI, yet they remain fundamentally limited by hallucination, unverifiable reasoning, and shallow evidence grounding. We argue that structure mining-rooted in decades of KDD research on taxonomy induction, ontology design, entity typing, and knowledge graph construction-is the key to overcoming these limitations. This tutorial presents a unified vision in which structuring serves as the enabling foundation for three pillars of next-generation LLM systems: (1) Structured Retrieval, where organizing corpora into ontology-guided multidimensional representations enables SQL-like queries that achieve substantially more precise and complete retrieval than similarity-based approaches; (2) Structured Reasoning, where grounding each inference step in typed, graph-structured evidence transforms opaque generation into auditable, verifiable reasoning chains; and (3) Structured Agent Memory, where multi-dimensional memory architectures bridge external corpus knowledge and experiential agent knowledge through a mutually enriching dual-memory design. Across all three pillars, we highlight how the cooperative interplay between classical KDD techniques and modern LLMs-where KDD defines structural schemas and quality constraints while LLMs execute flexible extraction and reasoning-creates systems that are more reliable, interpretable, and faithful. The tutorial covers both foundational methods and the latest advances (2024--2026), and concludes with open problems and future research directions at the intersection of data mining and LLMs.
Pengcheng Jiang, Jiashuo Sun, Wonbin Kweon et al.· Proceedings of the 32nd ACM...· 0 citations
Large scale agentic artificial intelligence systems retrieve evidence from vector databases that store dense embeddings alongside structured, numeric, and temporal attributes, and they turn that evidence into business decisions through repeated reasoning loops. Managing this multi-model data at enterprise scale raises three coupled questions: how to index billions of vectors so that retrieval is both accurate and fast, how to store them compactly enough to fit memory budgets, and how to engineer the decision loop so that it converges rather than drifts. This paper gives a unified mathematical and algorithmic treatment of these questions and introduces a proposed architecture, the Multi-Model Vector Loop Engine, that couples a quantized vector index with a feedback controlled agentic decision loop. We formalize approximate nearest neighbour retrieval, product quantization, hybrid multi-model filtering, and the decision loop as a fixed point iteration, and we prove that under a contraction condition the loop converges geometrically. We implement the full stack from first principles and report reproducible measurements on one hundred thousand 128-dimensional embeddings. An inverted file index raises recall at ten from 0.546 at a single probe to 1.000 at thirty two probes, product quantization trades memory for accuracy from recall 0.258 at 128 times compression to 0.701 at 16 times compression, a hybrid query with 4.0 percent selectivity resolves in 0.043 milliseconds, and the agentic loop converges to its fixed point within three iterations while raising cumulative coverage and modelled decision utility. A single ingestion shard encodes about 48800 records per second, so linear sharding reaches the five million records per second target with 103 shards. The results give practitioners a rigorous basis for managing vector and multi-model data under the accuracy, memory, and decision quality constraints of agentic enterprise systems.
Sudheer Singamsetty· International Journal of Com...· 0 citations
This paper presents AdaMM, a framework that jointly supports retrieval and analytic memory that extracts provenance-linked attribute-value observations from dialogue, images, and contextual metadata, discovers recurring field structures, and materializes them for analytical access.
Zhoujin Tian, Hao Zhang, Yao Tian et al.· arXiv.org· 0 citations
Structured data such as tabular data, time series and graphs powers many core data mining applications including recommendation, forecasting and user behavior analysis. Conventional approaches such as statistical models, classical machine learning methods and deep neural networks have achieved strong results. Yet most methods are designed for a single task or dataset and lack the ability to generalize across diverse structured data problems. Recent advances in foundation models point to a new direction for structured data modeling. Inspired by progress in natural language processing and computer vision, emerging research explores large-scale pretraining, synthetic data generation and in-context learning (ICL) to build more general-purpose models. In particular, tabular foundation models provide a promising path toward unifying heterogeneous structured modalities. This perspective treats tables as a common representation that can capture information from tabular data, time series, and graphs within a shared learning framework. Early studies show encouraging capabilities including cross-task generalization, few-shot adaptation and knowledge transfer across datasets. This tutorial presents a systematic overview of this emerging paradigm. We review classical foundations, introduce recent tabular foundation models, and discuss key challenges in pretraining data generation, model design, and multi-task learning.
Peng Cui, Xingxuan Zhang, Han-Jia Ye et al.· Proceedings of the 32nd ACM...· 0 citations
Information continuously evolves over time. Because of this dynamic nature, time becomes a fundamental dimension that shapes how we extract, retrieve, interpret, and reason about knowledge. As information systems are constantly updated, models must determine not only what is relevant, but also when that information is valid. This tutorial provides a structured and in-depth overview of the complete temporal information access pipeline: Temporal Information Extraction (TIE), Temporal Information Retrieval (TIR), and Temporal Question Answering (TQA). We examine the progression of temporal methods from early rule-based extraction and probabilistic retrieval to contemporary transformer-based and large language model (LLM) architectures. Participants gain a solid understanding of the core principles underlying the identification and normalization of time expressions, time-aware document ranking, and temporal reasoning in retrieval-augmented generation (RAG). The tutorial concludes with a discussion of open challenges and future research directions aimed at building AI systems that are temporally aware, robust, and adaptive. By connecting classical extraction and IR foundations with modern LLM-based reasoning, this tutorial presents a cohesive and up-to-date perspective on temporal information systems.
Bhawna Piryani, Avishek Anand, Omar Alonso et al.· Annual International ACM SIG...· 0 citations
Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce SearchWiki, a harness framework that synthesizes a corpus into a hierarchical, typed, navigable wiki and trains an agent, WikiResearcher-9B, to retrieve information through multi-turn tool use. The wiki organizes knowledge into three layers - document overviews, cross- document topic pages, and page-level source records; enabling progressive refinement of retrieval when initial lookup misses. We optimize the agent's navigation policy with on-policy reinforcement learning with a multi-component reward function balancing answer correctness, retrieval quality and trajectory efficiency. Evaluation on ViDoRe-V3 (8 domains), FinanceBench, and memory benchmarks (LoCoMo, LongMemEval, PersonaMem-v2) shows that WikiResearcher- 9B which is our RL-tuned Qwen 9B model, significantly outperforms same-size untrained baselines and exceeds or matches larger external models. SearchWiki paired with WikiResearcher-9B demonstrates that learned navigation over structured corpora is a superior alternative to flat retrieval.
Guransh Singh, Vishwajeet Kumar, Arkadeep Acharya et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
