RAM augments relational graph models with attribute-semantic retrieval via random-walk documents and two contrastive augmentations (ATRA, ETRA) to achieve state-of-the-art results on five real-world databases.
hub
Why Should I Trust You?
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 1
baseline 1
method 1
citation-polarity summary
representative citing papers
BRIDGE creates the first formal heterogeneous multi-dataset benchmark for IoT botnet detection with LODO evaluation, and TCH-Net achieves mean LODO F1 of 0.5577 while reaching F1 0.8296 on standard tests, outperforming twelve baselines.
WoodelfHD reduces Background SHAP preprocessing for decision trees from 3^D to 2^D complexity, enabling exact computation on depths up to 21 with reported speedups of 33x to 162x.
HCA combines knowledge graphs, KKT multipliers, and PCMCI to explain nonlinear MPC decisions, achieving 53% higher accuracy than LIME across three domains with a single parameter set.
TEmBed benchmark shows that the best tabular embedding model depends on the specific task and the representation level (cell, row, column, or table).
A jointly learned hierarchical index with cross-attention and residual quantization scales exact retrieval in foundational recommendation models, deployed at Meta with additional performance from test-time training on index nodes.
ExSTraQt uses quasi-temporal graph representations and supervised learning to detect suspicious transactions, achieving F1 score uplifts of up to 1% on real data and over 8% on synthetic datasets compared to prior AML models.
Presents REMOD, a graph-based supervised method for extracting semantic relations between entities in text to support modeling of online discourse and potential misinformation.
A CBR system based on similarity of local explanations provides visualizations that fraud analysts at a Dutch bank found useful and easy to use for processing ML-generated fraud alerts.
Human-grounded evaluation finds no significant performance improvement from adding SHAP explanations to model confidence scores in alert processing.
AgentStop uses execution signals to early-terminate failing local LLM agent trajectories, cutting energy use 15-20% with minimal utility loss.
A two-stage gradient boosted model with random effects predicts Arctic vessel movement probability (AUC 0.85) and conditional positive speed (77% out-of-fold variance explained), highlighting distance to coast and bathymetric depth as dominant factors.
A structured review of JSP 936 identifies eight challenge areas in operationalising AI assurance for UK Defence and concludes that further methods, guidance, and organisational capability are required.
LightGBM with team-level features outperforms a bank's existing rule-based change risk process on a one-year dataset while using SHAP for regulatory explainability.
citing papers explorer
-
From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analytics
RAM augments relational graph models with attribute-semantic retrieval via random-walk documents and two contrastive augmentations (ATRA, ETRA) to achieve state-of-the-art results on five real-world databases.
-
BRIDGE and TCH-Net: Heterogeneous Benchmark and Multi-Branch Baseline for Cross-Domain IoT Botnet Detection
BRIDGE creates the first formal heterogeneous multi-dataset benchmark for IoT botnet detection with LODO evaluation, and TCH-Net achieves mean LODO F1 of 0.5577 while reaching F1 0.8296 on standard tests, outperforming twelve baselines.
-
WOODELF-HD: Efficient Background SHAP for High-Depth Decision Trees
WoodelfHD reduces Background SHAP preprocessing for decision trees from 3^D to 2^D complexity, enabling exact computation on depths up to 21 with reported speedups of 33x to 162x.
-
Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive Control
HCA combines knowledge graphs, KKT multipliers, and PCMCI to explain nonlinear MPC decisions, achieving 53% higher accuracy than LIME across three domains with a single parameter set.
-
Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks
TEmBed benchmark shows that the best tabular embedding model depends on the specific task and the representation level (cell, row, column, or table).
-
Efficient Retrieval Scaling with Hierarchical Indexing for Large Scale Recommendation
A jointly learned hierarchical index with cross-attention and residual quantization scales exact retrieval in foundational recommendation models, deployed at Meta with additional performance from test-time training on index nodes.
-
Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation
ExSTraQt uses quasi-temporal graph representations and supervised learning to detect suspicious transactions, achieving F1 score uplifts of up to 1% on real data and over 8% on synthetic datasets compared to prior AML models.
-
REMOD: Relation Extraction for Modeling Online Discourse
Presents REMOD, a graph-based supervised method for extracting semantic relations between entities in text to support modeling of online discourse and potential misinformation.
-
Case-Based Reasoning for Assisting Domain Experts in Processing Fraud Alerts of Black-Box Machine Learning Models
A CBR system based on similarity of local explanations provides visualizations that fraud analysts at a Dutch bank found useful and easy to use for processing ML-generated fraud alerts.
-
A Human-Grounded Evaluation of SHAP for Alert Processing
Human-grounded evaluation finds no significant performance improvement from adding SHAP explanations to model confidence scores in alert processing.
-
AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices
AgentStop uses execution signals to early-terminate failing local LLM agent trajectories, cutting energy use 15-20% with minimal utility loss.
-
A Gradient Boosted Mixed-Model Machine Learning Framework for Vessel Speed in the U.S. Arctic
A two-stage gradient boosted model with random effects predicts Arctic vessel movement probability (AUC 0.85) and conditional positive speed (77% out-of-fold variance explained), highlighting distance to coast and bathymetric depth as dominant factors.
-
AI Assurance in UK Defence: Challenges in Operationalising JSP 936
A structured review of JSP 936 identifies eight challenge areas in operationalising AI assurance for UK Defence and concludes that further methods, guidance, and organisational capability are required.
-
Learning from Change: Predictive Models for Incident Prevention in a Regulated IT Environment
LightGBM with team-level features outperforms a bank's existing rule-based change risk process on a one-year dataset while using SHAP for regulatory explainability.
- The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction