@inproceedings{ning-etal-2026-hta,
title = "{HTA}: Temporal Reasoning Transformer with Temporal Context Encoding for Temporal Knowledge Graph Forecasting",
author = "Ning, Yingsong and
Zhang, Fu and
Cheng, Jingwei and
Peng, Jiashun and
Wang, Xiaoke",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2041/",
pages = "43440--43453",
ISBN = "979-8-89176-462-0",
abstract = "Temporal knowledge graph (TKG) forecasting aims to predict future facts based on historical temporal information and still faces key challenges such as event sparsity and complex long-term dependencies. While graph-based methods effectively capture relational structure, they often fail to model nuanced long-range temporal patterns. Alternatively, standard Transformers, while potent for sequence modeling, are fundamentally time-agnostic; their generic positional encodings overlook critical TKG-specific temporal dynamics. As a result, many approaches struggle to capture fine-grained temporal patterns, limiting their effectiveness in forecasting sparse or complex events. To address these limitations, we propose HTA (Hybrid Transformer Architecture). HTA first constructs a query-specific Attention-Ready Temporal Sequence (ARTS) by aggregating historical context along a query-centered temporal reasoning path. This atomic sequence represents timestamps as dedicated temporal tokens that are contextualized together with their associated relation and entity tokens. At its core, HTA employs a stack of hybrid Attention-Mixer Transformer Blocks that combine bidirectional self-attention for capturing long-range dependencies with MLP-based layers for efficient feature refinement. Extensive experiments on four diverse benchmarks show that HTA achieves state-of-the-art performance. Notably, on the sparse and challenging GDELT dataset, HTA achieves an absolute MRR improvement of over 18 points, demonstrating its superior ability to model complex and noisy temporal dynamics."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ning-etal-2026-hta">
<titleInfo>
<title>HTA: Temporal Reasoning Transformer with Temporal Context Encoding for Temporal Knowledge Graph Forecasting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yingsong</namePart>
<namePart type="family">Ning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiashun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoke</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Temporal knowledge graph (TKG) forecasting aims to predict future facts based on historical temporal information and still faces key challenges such as event sparsity and complex long-term dependencies. While graph-based methods effectively capture relational structure, they often fail to model nuanced long-range temporal patterns. Alternatively, standard Transformers, while potent for sequence modeling, are fundamentally time-agnostic; their generic positional encodings overlook critical TKG-specific temporal dynamics. As a result, many approaches struggle to capture fine-grained temporal patterns, limiting their effectiveness in forecasting sparse or complex events. To address these limitations, we propose HTA (Hybrid Transformer Architecture). HTA first constructs a query-specific Attention-Ready Temporal Sequence (ARTS) by aggregating historical context along a query-centered temporal reasoning path. This atomic sequence represents timestamps as dedicated temporal tokens that are contextualized together with their associated relation and entity tokens. At its core, HTA employs a stack of hybrid Attention-Mixer Transformer Blocks that combine bidirectional self-attention for capturing long-range dependencies with MLP-based layers for efficient feature refinement. Extensive experiments on four diverse benchmarks show that HTA achieves state-of-the-art performance. Notably, on the sparse and challenging GDELT dataset, HTA achieves an absolute MRR improvement of over 18 points, demonstrating its superior ability to model complex and noisy temporal dynamics.</abstract>
<identifier type="citekey">ning-etal-2026-hta</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2041/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>43440</start>
<end>43453</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HTA: Temporal Reasoning Transformer with Temporal Context Encoding for Temporal Knowledge Graph Forecasting
%A Ning, Yingsong
%A Zhang, Fu
%A Cheng, Jingwei
%A Peng, Jiashun
%A Wang, Xiaoke
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F ning-etal-2026-hta
%X Temporal knowledge graph (TKG) forecasting aims to predict future facts based on historical temporal information and still faces key challenges such as event sparsity and complex long-term dependencies. While graph-based methods effectively capture relational structure, they often fail to model nuanced long-range temporal patterns. Alternatively, standard Transformers, while potent for sequence modeling, are fundamentally time-agnostic; their generic positional encodings overlook critical TKG-specific temporal dynamics. As a result, many approaches struggle to capture fine-grained temporal patterns, limiting their effectiveness in forecasting sparse or complex events. To address these limitations, we propose HTA (Hybrid Transformer Architecture). HTA first constructs a query-specific Attention-Ready Temporal Sequence (ARTS) by aggregating historical context along a query-centered temporal reasoning path. This atomic sequence represents timestamps as dedicated temporal tokens that are contextualized together with their associated relation and entity tokens. At its core, HTA employs a stack of hybrid Attention-Mixer Transformer Blocks that combine bidirectional self-attention for capturing long-range dependencies with MLP-based layers for efficient feature refinement. Extensive experiments on four diverse benchmarks show that HTA achieves state-of-the-art performance. Notably, on the sparse and challenging GDELT dataset, HTA achieves an absolute MRR improvement of over 18 points, demonstrating its superior ability to model complex and noisy temporal dynamics.
%U https://aclanthology.org/2026.findings-emnlp.2041/
%P 43440-43453
Markdown (Informal)
[HTA: Temporal Reasoning Transformer with Temporal Context Encoding for Temporal Knowledge Graph Forecasting](https://aclanthology.org/2026.findings-emnlp.2041/) (Ning et al., Findings 2026)
ACL