Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding

• URL: http://arxiv.org/abs/2608.24273v2
• Date: Wed, 26 Aug 2026 13:19:03 GMT
• Title: Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding
• Abstract summary: We formalize candidate-set interference as candidate-set interference and introduce Matched Excess-Outranker Regularization (MEOR)<n>MEOR compares smooth answer-relative newcomer pressure with score-blind, structurally matched old references.<n>It improves historical current-universe mean reciprocal rank (MRR) by 0.0057 over replay and reduces candidate-set interference by 0.0055, with one-sided 95% lower bounds of 0.0052 and 0.0051, respectively.
• Score: 32.598018815734335
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual knowledge graph embedding updates entity and relation representations as a graph grows. Existing methods primarily address catastrophic forgetting, but entity admission also changes the candidate universe of every compatible query. A historical answer can therefore lose rank even when its score and its ordering among old entities are preserved. We formalize this effect as candidate-set interference and introduce Matched Excess-Outranker Regularization (MEOR), a host-level objective that compares smooth answer-relative newcomer pressure with score-blind, structurally matched old references. Its one-sided penalty acts only when newcomer competition exceeds the matched reference, preserving the host learner's signal for legitimate new entities. Across eight paired runs on ENTITY-ComplEx, MEOR improves historical current-universe mean reciprocal rank (MRR) by 0.0057 over replay and reduces candidate-set interference by 0.0055, with one-sided 95% lower bounds of 0.0052 and 0.0051, respectively. It satisfies the preservation criteria for old-universe ranking and newcomer acquisition and improves historical current-universe MRR over persistent calibration, matched maximum regularizer (MMR), and unmatched old regularizer (UOR). Direct ablations support each component of its reference construction and aggregation. Adding MEOR also improves historical ranking in all ten reported FBInc-S and FBInc-L host and backbone settings, with every paired 95% confidence interval excluding zero. These results establish candidate admission as a distinct source of continual rank loss and show that it can be controlled without replacing the underlying embedding architecture or continual learner.

Related papers

• Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection [66.44527094471619]
  We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns.<n>On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99%, 99.93%, and 99.99%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-09-15T00:31:01Z)
• Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems [40.47928908205563]
  Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection.<n>Despite strong empirical results, these systems lack a unified account of coordination, memory improvement, and the role of external verification.<n>We provide confidence gating for evaluation and re-anchoring guarantees for piecewise-stationary environments.<n>Experiments instantiate these objects with environment-grounded metrics and test the predicted coordination and drift laws.
  arXiv  Detail & Related papers  (2026-09-02T15:50:10Z)
• CHASE: How Content Ecosystems Are Reshaped When Ranking Is the Only Target [1.5223740593989443]
  We introduce Content Homogenization under rAnking Signal Exploitation (CHASE), a controlled simulation framework for studying how content ecosystems are reshaped.<n>We show how repeated optimization against a fixed LLM ranking signal can reshape both content populations and the incentives faced by content creators.
  arXiv  Detail & Related papers  (2026-08-31T08:53:56Z)
• Counterfactual Bias Testing for Application Tracking System [1.007765066765576]
  This paper uses task-specialized LLM agents to synthesize identity-neutral base resumes and inject demographic treatments.<n>It ranks candidates against a job description via a fine-tuned sentence-embedding model and cosine similarity.<n>It computes a nine-metric fairness suite spanning counterfactual (score delta, mean absolute rank change, flip rate), group-fairness (top-K retention, four-fifths/impact ratio), and merit-aware (Recall@K, nDCG@K, equal opportunity, equalized odds) families.
  arXiv  Detail & Related papers  (2026-08-27T10:01:36Z)
• Benchmarking Recursive-Collapse Warning Claims Under Matched False-Positive Control [0.0]
  Recursive systems can enter collapse-like regimes before overt failure becomes visible.<n>We introduce Loopzero, a claim-bounded benchmark framework for testing whether failures follow a directional telemetry pattern.<n>We evaluate the bridge on two frozen public-artifact benchmarks.
  arXiv  Detail & Related papers  (2026-05-29T20:12:42Z)
• F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking [79.49893545611779]
  Large Language Models (LLMs) can generate a subset and order it within a single autoregressive pass.<n>This flexibility introduces a new optimization challenge: the model must search an output space while receiving utility feedback only after the full ranked list is generated.<n>This credit assignment gap makes end-to-end optimization unstable and sample-inefficient.<n>We propose a unified framework that performs both within a single autoregressive rollout and optimize them end-to-end via factorized group-relative policy optimization.
  arXiv  Detail & Related papers  (2026-05-13T04:52:33Z)
• AdaPaD: Adaptive Parallel Deflation for PEFT with Self-Correcting Rank Discovery [10.176501817419371]
  We present AdaPaD (Adaptive Parallel Deflation), which trains all rank-1 components simultaneously.<n>We prove that every component's error decays exponentially after a warm-up period.<n>AdaPaD is competitive with adaptive-rank LoRA baselines on GLUE with DeBERTaV3-base at matched parameter budgets.
  arXiv  Detail & Related papers  (2026-05-11T15:44:13Z)
• UniRank: Unified List-wise Reranking via Confidence-Ordered Denoising [33.296591996616975]
  List-wise reranking arranges a request-specific pool of candidate items into an ordered slate that maximizes user satisfaction.<n>We present UniRank, a unified list-wise reranking framework whose inference time variants recover AR and NAR rerankers as special cases.<n>Experiments on Amazon Books, MovieLens-1M, and an industrial short video dataset show that UniRank consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-11T13:12:23Z)
• FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation [73.22935457705057]
  We introduce FRESCO, a benchmark for evaluating re-rankers in temporally dynamic contexts.<n>By pairing recency-seeking queries with historical Wikipedia revisions, FRESCO tests whether re-rankers can prioritize factually recent evidence while maintaining semantic relevance.<n>Our evaluation reveals a consistent failure mode across existing re-rankers: a strong bias toward older, semantically rich documents, even when they are factually obsolete.
  arXiv  Detail & Related papers  (2026-04-14T17:04:25Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Post Hoc Regression Refinement via Pairwise Rankings [37.14333704508996]
  RankRefine is a model-agnostic, plug-and-play method that refines regression with expert knowledge coming from pairwise rankings.<n>In molecular property prediction task, RankRefine achieves up to 10% relative reduction in mean absolute error.
  arXiv  Detail & Related papers  (2025-08-22T16:17:31Z)
• Gumbel Reranking: Differentiable End-to-End Reranker Optimization [61.16471123356738]
  RAG systems rely on rerankers to identify relevant documents.<n> fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs.<n>We propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap.
  arXiv  Detail & Related papers  (2025-02-16T13:23:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.