Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction

• URL: http://arxiv.org/abs/2609.06731v1
• Date: Sun, 06 Sep 2026 17:03:18 GMT
• Title: Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction
• Abstract summary: Temporal relation extraction determines whether an event occurs before, after, or simultaneously with another event.<n>We propose a theoretically grounded architecture, Convolutional Bottleneck Interaction (CBI), which first applies lightweight depthwise convolution to enhance event representations.<n>CBI provides consistent and substantial gains, up to +31.7 micro F1, while adding minimal computational cost.
• Score: 38.03753717118107
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Temporal relation extraction determines whether an event occurs before, after, or simultaneously with another event, and therefore relies on accurately modeling how the two events interact. Mainstream systems achieve this by concatenating event spans or using shallow fusion, which works well when all model parameters are trainable. However, in parameter-efficient fine-tuning, low-rank bottlenecks restrict information flow and prevent these interaction signals from passing through, leading to clear performance drops. To address this limitation, we propose a theoretically grounded architecture, Convolutional Bottleneck Interaction (CBI), which first applies lightweight depthwise convolution to enhance event representations and then uses element-wise multiplication to capture effective event-event interactions inside the bottleneck. Across five datasets and seven backbone models in the Adapter and LoRA settings, CBI provides consistent and substantial gains, up to +31.7 micro F1, while adding minimal computational cost, showing that explicit interaction inside low-rank spaces is crucial for temporal relation extraction. The code is available at https://github.com/VRCMF/CIF.git.

Related papers

• Following the Flow: Advection-Consistent Modeling for Event-based Small Object Detection [2.925778409623925]
  Event cameras enable high-frequency visual perception with microsecond latency, offering advantages for dynamic scenes.<n>However, event-based small object detection remains challenging due to sparse asynchronous measurements and weak object responses that are easily disrupted by noise.<n>We propose a physics-guided advection-consistent framework, termed PACT, which formulates event evolution as a motion-driven feature transport process.
  arXiv  Detail & Related papers  (2026-06-21T07:56:34Z)
• TIE: Time Interval Encoding for Video Generation over Events [50.66585165263848]
  Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events.<n>Modern video generators represent time as discrete points through point-wise positional encodings.<n>Time Interval TIE is a principled, plug-and-play interval-aware generalization.
  arXiv  Detail & Related papers  (2026-05-11T13:23:14Z)
• Rethinking Event-Based Object Dtection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning [65.08890312027314]
  Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range.<n>Event Dual Temporal-Relational Aggregation Detector (Ev-DTAD) integrates representation-level temporal encoding with model-level temporal-hypergraph reasoning.<n>We show that Ev-DTAD achieves a competitive accuracy-efficiency trade-off, validating the complementarity between compact temporal representation and temporal-hypergraph feature reasoning.
  arXiv  Detail & Related papers  (2026-05-09T09:20:34Z)
• TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction [3.8264010687414953]
  Temporal graph link prediction aims to predict future interactions between nodes in a graph based on their historical interactions.<n>We propose a novel framework called TAMI, which contains two effective components, namely log time encoding function and link history aggregation.
  arXiv  Detail & Related papers  (2025-10-23T05:14:58Z)
• Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba [11.400397931501338]
  Event cameras draw inspiration from biological systems, boasting low latency and high dynamic range while consuming minimal power.<n>Most current approach to processing Event Cloud often involves converting it into frame-based representations.<n>We propose EventMamba, an efficient and effective framework based on Point Cloud representation.
  arXiv  Detail & Related papers  (2024-05-09T21:47:46Z)
• Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization [31.065768513381414]
  Document-level multi-event extraction aims to extract structural information from a given document automatically. We propose an alternative approach for document-level multi-event extraction with event proxy nodes and Hausdorff distance minimization. Our model outperforms previous state-of-the-art method in F1-score on two datasets with only a fraction of training time.
  arXiv  Detail & Related papers  (2023-05-30T10:33:05Z)
• MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction [78.61546292830081]
  We construct a large-scale human-annotated ERE dataset MAVEN-ERE with improved annotation schemes. It contains 103,193 event coreference chains, 1,216,217 temporal relations, 57,992 causal relations, and 15,841 subevent relations. Experiments show that ERE on MAVEN-ERE is quite challenging, and considering relation interactions with joint learning can improve performances.
  arXiv  Detail & Related papers  (2022-11-14T13:34:49Z)
• AEGNN: Asynchronous Event-based Graph Neural Networks [54.528926463775946]
  Event-based Graph Neural Networks generalize standard GNNs to process events as "evolving"-temporal graphs. AEGNNs are easily trained on synchronous inputs and can be converted to efficient, "asynchronous" networks at test time.
  arXiv  Detail & Related papers  (2022-03-31T16:21:12Z)
• Spatio-Temporal Action Detection with Multi-Object Interaction [127.85524354900494]
  In this paper, we study the S-temporal action detection problem with multi-object interaction. We introduce a new dataset that is spatially annotated with action tubes containing multi-object interactions. We propose an end-to-endtemporal action detection model that performs both spatial and temporal regression simultaneously.
  arXiv  Detail & Related papers  (2020-04-01T00:54:56Z)

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.