Implicit Semantic-Aware Communication Based on Hypergraph Reasoning

Guangming Shi; Shurui Tu; Yingyu Li; Yiwei Liao; Yong Xiao

arxiv: 2606.20162 · v1 · pith:JNK2Z373new · submitted 2026-06-18 · 💻 cs.AI · cs.IT· cs.NI· math.IT

Implicit Semantic-Aware Communication Based on Hypergraph Reasoning

Yiwei Liao , Shurui Tu , Yong Xiao , Yingyu Li , Guangming Shi This is my paper

Pith reviewed 2026-06-26 17:34 UTC · model grok-4.3

classification 💻 cs.AI cs.ITcs.NImath.IT

keywords semantic communicationhypergraph reasoningimplicit semanticssemantic inferencehigher-order relationsinformation loss

0 comments

The pith

Hypergraph reasoning models multi-entity semantic relations in subspaces to improve inference under information loss.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper claims that representing semantic knowledge as hypergraphs, rather than pairwise graphs, captures higher-order implicit correlations such as group interactions and complex contexts. Entities and relations are then mapped into dedicated semantic subspaces to disentangle interactions and avoid over-smoothing. This enables more reliable semantic recovery at the receiver even when transmission causes partial information loss. The central demonstration is that the resulting HISR framework raises implicit semantic interpretation accuracy by up to 36.6 percent compared with prior graph-based benchmarks.

Core claim

The HISR framework leverages hypergraphs to represent complex multi-entity relationships among semantic knowledge entities. In HISR, entities and their associated higher-order relations are mapped into dedicated semantic subspaces tailored to distinct relational contexts. This design disentangles diverse semantic interactions to mitigate the over-smoothing effects commonly found in traditional graph embedding methods and enables robust semantic inference even when partial information loss occurs during transmission.

What carries the argument

Hypergraph encoding of higher-order semantic relations, followed by projection into context-specific semantic subspaces that separate interactions.

If this is right

Semantic communication systems gain the ability to handle group interactions and multi-entity associations without rapid performance drop under noise.
Inference remains functional when some transmitted semantic elements are corrupted or erased.
Over-smoothing that collapses distinct meanings in graph embeddings is reduced by the subspace separation step.
The shift from bit-level to meaning-level transmission becomes more practical for real-world relational data.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The subspace-mapping idea could be tested on temporal hypergraphs to track how semantic relations evolve across successive messages.
Combining the hypergraph layer with existing message-passing neural networks might produce a hybrid encoder that inherits both higher-order expressivity and efficient training.
The same disentanglement technique may transfer to other partial-observation settings such as sensor networks or multi-agent coordination where only subsets of relations are observed.

Load-bearing premise

Hypergraphs can represent higher-order implicit correlations among semantic entities and subspace mapping will separate those interactions enough to support inference despite missing data.

What would settle it

An experiment that applies HISR and standard graph methods to the same semantic messages under identical partial-information-loss conditions and finds no accuracy gain, or a loss, for HISR would falsify the claim.

Figures

Figures reproduced from arXiv: 2606.20162 by Guangming Shi, Shurui Tu, Yingyu Li, Yiwei Liao, Yong Xiao.

**Figure 2.** Figure 2: The proposed HISR architecture: Semantic Extraction, Relation-Specific Subspace Modeling, Knowledge Base and Implicit Semantic [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗

**Figure 3.** Figure 3: Information completion based on relation-specific semantic [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗

**Figure 4.** Figure 4: Example of Implicit Semantic Inference via Relation-Specific [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗

**Figure 5.** Figure 5: Training, validation, and test loss curves of HISR on the Cora dataset. [PITH_FULL_IMAGE:figures/full_fig_p013_5.png] view at source ↗

**Figure 8.** Figure 8: Reasoning accuracy and running time under different numbers of semantic subspaces on the Pubmed dataset. consistently decreases and converges smoothly, demonstrating stable and efficient optimization of the semantic model. Validation (dashed orange line) and test losses (solid green line) similarly exhibit steady convergence and ultimately stabilize at low values, indicating effective generalization and … view at source ↗

**Figure 12.** Figure 12: Inference accuracy of HISR under different SNR on the M-FB15K dataset. sification accuracy in these categories. Although some misclassifications occur, they are generally minor and concentrated around semantically similar categories, reflecting the model’s effectiveness in capturing complex semantic relationships [PITH_FULL_IMAGE:figures/full_fig_p014_12.png] view at source ↗

**Figure 18.** Figure 18: Impact of embedding dimension on classification accuracy on the Pubmed dataset. The observed performance saturation at higher SNR levels can be explained as follows. Initially, increasing the SNR significantly reduces communication noise and channel-induced distortion, thereby substantially improving semantic inference accuracy. However, beyond a certain SNR threshold, the inference performance improv… view at source ↗

**Figure 15.** Figure 15: Accuracy of semantic recovery when the channel experiences additive Rayleigh noise under different SNRs on the Cora dataset. [PITH_FULL_IMAGE:figures/full_fig_p015_15.png] view at source ↗

read the original abstract

Semantic-aware communication has emerged as a transformative paradigm for next-generation communication systems, shifting the fundamental goal from transmitting bit-level symbols to reliably recovering and understanding the semantic meaning of information. Previous studies have demonstrated that representing the semantic content of source messages as graph-based structures can significantly improve communication efficiency and the accuracy of semantic inference at the receiver. However, existing solutions typically employ graphs that capture only pairwise relationships, thereby neglecting higher-order implicit correlations commonly observed in real-world scenarios, such as group interactions, multi-entity associations, and complex relational contexts. This limitation reduces semantic expressiveness and makes semantic inference susceptible to ambiguity and performance degradation, particularly under noisy or corrupted channel conditions. To address these issues, this paper proposes a novel hypergraph-based implicit semantic reasoning framework, HISR, which leverages hypergraphs to represent complex multi-entity relationships among semantic knowledge entities. In HISR, entities and their associated higher-order relations are mapped into dedicated semantic subspaces tailored to distinct relational contexts. This design not only disentangles diverse semantic interactions to mitigate the over-smoothing effects commonly found in traditional graph embedding methods but also enables robust semantic inference even when partial information loss occurs during transmission. Numerical results show that the proposed HISR achieves up to a 36.6% improvement in implicit semantic interpretation accuracy over the state-of-the-art benchmarks.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper extends graph-based semantic comms to hypergraphs for higher-order relations and claims a 36.6% accuracy gain, but the abstract supplies no experimental details to support that number.

read the letter

The core idea here is to replace pairwise graphs with hypergraphs so that semantic communication systems can capture group-level and multi-entity relations that current methods miss. The authors map entities into separate semantic subspaces to reduce over-smoothing and keep inference stable when some information drops out in the channel. That framing directly targets a limitation they identify in prior work.

The paper does a clean job stating the problem and sketching how hypergraphs plus subspace separation could help. The description of HISR is concrete enough that someone already working on graph neural nets for networks could see where to plug it in.

The soft spot is the results. The 36.6% figure appears without any dataset names, baseline descriptions, channel models, or error statistics. From the abstract alone it is impossible to judge whether the gain is real, reproducible, or tied to particular choices in the setup. The full manuscript is referenced but not supplied here, so I cannot check whether the methods section or any derivations close that gap.

This is aimed at people already inside semantic communication and AI-assisted networks. A reader who follows graph-based semantic work would get a usable new modeling option to test, but would still need the missing experimental protocol before treating the number as settled.

The thinking is coherent on its own terms and engages the cited literature without obvious circularity. It deserves a serious referee to examine the experiments and any code or proofs that may be in the full text rather than a desk reject.

Referee Report

1 major / 0 minor

Summary. The paper proposes the HISR framework, a hypergraph-based approach to implicit semantic reasoning for semantic-aware communication. It claims that standard graphs capture only pairwise relations and thus miss higher-order implicit correlations; HISR maps semantic entities and their higher-order relations into dedicated subspaces to reduce over-smoothing and support inference under partial information loss, reporting up to a 36.6% gain in implicit semantic interpretation accuracy over existing benchmarks.

Significance. If the performance claim is substantiated, the work would address a recognized limitation of pairwise graph models in semantic communication and could improve robustness under noisy channels. No machine-checked proofs, reproducible code, or parameter-free derivations are described, so the significance rests entirely on the empirical result.

major comments (1)

[Abstract] Abstract: the central numerical claim of a 36.6% accuracy improvement is stated without any description of the datasets, baseline methods, experimental protocol, number of trials, error bars, or statistical tests. This absence prevents verification that the data and methods support the stated result and is load-bearing for the paper's primary contribution.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive comment on the abstract. We agree that the central numerical claim requires supporting context to allow verification.

read point-by-point responses

Referee: [Abstract] Abstract: the central numerical claim of a 36.6% accuracy improvement is stated without any description of the datasets, baseline methods, experimental protocol, number of trials, error bars, or statistical tests. This absence prevents verification that the data and methods support the stated result and is load-bearing for the paper's primary contribution.

Authors: We agree that the abstract as currently written does not provide sufficient context for the 36.6% claim. The revised abstract will include a concise statement identifying the datasets, the main baseline methods, the experimental protocol (including number of trials), and the reporting of error bars. This change will be made without altering the length or focus of the abstract. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The abstract and context provide no equations, derivations, or load-bearing steps that reduce any claim to a fitted input, self-definition, or self-citation chain. The framework is introduced as a distinct proposal using hypergraphs for higher-order relations, with the 36.6% improvement stated as a numerical result rather than a constructed prediction. No self-citations, ansatzes, or uniqueness theorems are referenced in a way that would create circularity. This is the expected self-contained case.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

Review is based solely on the abstract; full details on parameters, assumptions, and entities are unavailable. The ledger reflects only what is stated at high level.

axioms (1)

domain assumption Hypergraphs can represent higher-order implicit correlations in semantic knowledge entities better than pairwise graphs
Core premise invoked to justify moving beyond existing graph methods for semantic content.

invented entities (1)

HISR framework no independent evidence
purpose: To perform implicit semantic reasoning by mapping entities and higher-order relations into semantic subspaces
Newly introduced method whose performance is claimed in the abstract

pith-pipeline@v0.9.1-grok · 5773 in / 1267 out tokens · 42079 ms · 2026-06-26T17:34:05.850129+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

27 extracted references · 1 canonical work pages

[1]

Hypergraph reason- ing for implicit semantic-aware communication,

S. Tu, Y. Liao, Y. Xiao, Y. Li, and G. Shi, “Hypergraph reason- ing for implicit semantic-aware communication,” in Proc. IEEE Global Commun. Conf. (GLOBECOM) Workshops, Taipei, China, Dec. 2025

2025
[2]

From semantic communi- cation to Semantic-Aware networking: Model, architecture, and open problems,

G. Shi, Y. Xiao, Y. Li, and X. Xie, “From semantic communi- cation to Semantic-Aware networking: Model, architecture, and open problems,” IEEE Commun. Mag., vol. 59, no. 8, pp. 44–50, Aug. 2021

2021
[3]

SANet: A semantic-aware agentic AI networking framework for cross-layer optimization in 6G,

Y. Xiao, X. Li, H. Zhou, Y. Gao, G. Shi, P. Zhang, and M. Krunz, “SANet: A semantic-aware agentic AI networking framework for cross-layer optimization in 6G,” IEEE Trans. Mobile Comput., 2026

2026
[4]

An introduction to semantic communica- tion and Semantic-Aware networking standardization for 6G,

G. Shi and Y. Xiao, “An introduction to semantic communica- tion and Semantic-Aware networking standardization for 6G,” GetMobile: Mobile Comput. and Commun., vol. 28, no. 3, pp. 14–19, Oct. 2024

2024
[5]

SANSee: A physical-layer semantic-aware networking framework for distributed wireless sensing,

H. Zhu, Y. Xiao, Y. Li, G. Shi, and M. Krunz, “SANSee: A physical-layer semantic-aware networking framework for distributed wireless sensing,” IEEE Trans. Mobile Comput., vol. 24, no. 3, pp. 1636–1653, Mar. 2025

2025
[6]

Reasoning over the air: A Reasoning-Based Implicit Semantic-Aware Communication framework,

Y. Xiao, Y. Liao, Y. Li, G. Shi, H. V. Poor, W. Saad, M. Debbah, and M. Bennis, “Reasoning over the air: A Reasoning-Based Implicit Semantic-Aware Communication framework,” IEEE Trans. Wireless Commun., vol. 23, no. 4, pp. 3839–3855, Apr. 2024

2024
[7]

Imitation Learning-based Implicit Semantic-aware Communication Net- works: Multi-layer Representation and Collaborative Reason- ing,

Y. Xiao, Z. Sun, G. Shi, and D. Niyato, “Imitation Learning-based Implicit Semantic-aware Communication Net- works: Multi-layer Representation and Collaborative Reason- ing,” IEEE J. Sel. Areas Commun., vol. 41, no. 3, pp. 639–658, Mar. 2023

2023
[8]

Joint Source–Channel Coding: Fundamentals and recent progress in practical designs,

D. Gunduz et al., “Joint Source–Channel Coding: Fundamentals and recent progress in practical designs,” Proc. IEEE, pp. 1–32, 2024

2024
[9]

Implicit semantic communication based on Bayesian reconstruction framework,

Y. Liao, S. Tu, Y. Zhou, D. Jin, Y. Xiao, and Y. Li, “Implicit semantic communication based on Bayesian reconstruction framework,” IEEE Wireless Commun. Lett., vol. 15, pp. 430– 434, 2026

2026
[10]

On the rep- resentation and embedding of knowledge bases beyond binary relations,

J. Wen, J. Li, Y. Mao, S. Chen, and R. Zhang, “On the rep- resentation and embedding of knowledge bases beyond binary relations,” in Proc. Int. Joint Conf. Artif. Intell. (IJCAI), New York, NY, USA, Jul. 2016, pp. 1300–1307

2016
[11]

Role-aware modeling for N-ary relational knowledge bases,

Y. Liu, Q. Yao, and Y. Li, “Role-aware modeling for N-ary relational knowledge bases,” in Proc. Web Conf. 2021, New York, NY, USA, Jun. 2021, pp. 2660–2671

2021
[12]

Inference of Hyperedges and overlapping communities in Hypergraphs,

M. Contisciani, F. Battiston, and C. De Bacco, “Inference of Hyperedges and overlapping communities in Hypergraphs,” Nature Commun., vol. 13, no. 1, p. 7229, Nov. 2022

2022
[13]

Community detection in Hypergraphs: Optimal statistical limit and eﬀicient algorithms,

I. Chien, C.-Y. Lin, and I.-H. Wang, “Community detection in Hypergraphs: Optimal statistical limit and eﬀicient algorithms,” in Proc. Int. Conf. Artif. Intell. Statist. (AISTATS), vol. 84, Playa Blanca, Spain, Apr. 2018, pp. 871–879

2018
[14]

A survey on Hypergraph Representation Learn- ing,

A. Antelmi, G. Cordasco, M. Polato, V. Scarano, C. Spagnuolo, and D. Yang, “A survey on Hypergraph Representation Learn- ing,” ACM Comput. Surv., vol. 56, no. 1, p. Art. no. 24, Aug. 2023

2023
[15]

Hypergraph Learning: Methods and practices,

Y. Gao, Z. Zhang, H. Lin, X. Zhao, S. Du, and C. Zou, “Hypergraph Learning: Methods and practices,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 5, pp. 2548–2566, May 2022

2022
[16]

Deeper insights into Graph Con- volutional Networks for Semi-Supervised Learning,

Q. Li, Z. Han, and X.-m. Wu, “Deeper insights into Graph Con- volutional Networks for Semi-Supervised Learning,” in Proc. AAAI Conf. Artif. Intell., vol. 32, no. 1, New Orleans, LA, USA, Apr. 2018, pp. 3538–3545

2018
[17]

Not too little, not too much: A theoretical analysis of Graph (over) smoothing,

N. Keriven, “Not too little, not too much: A theoretical analysis of Graph (over) smoothing,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), New Orleans, LA, USA, Dec. 2022

2022
[18]

Preventing Over- Smoothing for Hypergraph Neural Networks,

G. Chen, J. Zhang, X. Xiao, and Y. Li, “Preventing Over- Smoothing for Hypergraph Neural Networks,” arXiv preprint, 2022, arXiv:2203.17159

work page arXiv 2022
[19]

Hypergraph Neural Networks,

Y. Feng, H. You, Z. Zhang, R. Ji, and Y. Gao, “Hypergraph Neural Networks,” in Proc. AAAI Conf. Artif. Intell., Honolulu, HI, USA, Jul. 2019, pp. 3558–3565

2019
[20]

HGNN+: General hypergraph neural networks,

Y. Gao, Y. Feng, S. Ji, and R. Ji, “HGNN+: General hypergraph neural networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 3, pp. 3181–3199, Mar. 2023

2023
[21]

Generalizing tensor decomposition for N-ary relational knowledge bases,

Y. Liu, Q. Yao, and Y. Li, “Generalizing tensor decomposition for N-ary relational knowledge bases,” in Proc. Web Conf. 2020, Taipei, China, Apr. 2020, pp. 1104–1114

2020
[22]

Hyperbolic Graph Convolutional Neural Networks,

I. Chami, Z. Ying, C. Ré, and J. Leskovec, “Hyperbolic Graph Convolutional Neural Networks,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 32, Vancouver, BC, Canada, Dec. 2019

2019
[23]

Knowledge Graph Embedding for Link Prediction: A compar- ative analysis,

A. Rossi, D. Barbosa, D. Firmani, A. Matinata, and P. Merialdo, “Knowledge Graph Embedding for Link Prediction: A compar- ative analysis,” ACM Trans. Knowl. Discov. Data, vol. 15, no. 2, p. Art. no. 14, Jan. 2021

2021
[24]

Knowledge Graph Embedding by translating on hyperplanes,

Z. Wang, J. Zhang, J. Feng, and Z. Chen, “Knowledge Graph Embedding by translating on hyperplanes,” in Proc. AAAI Conf. Artif. Intell., Quebec City, QC, Canada, Jun. 2014, pp. 1112–1119

2014
[25]

A theory of semantic communication,

Y. Shao, Q. Cao, and D. Gündüz, “A theory of semantic communication,” IEEE Transactions on Mobile Computing, vol. 23, no. 12, pp. 12 211–12 228, Dec 2024

2024
[26]

Modeling relational data with Graph Convolutional Networks,

M. Schlichtkrull, T. N. Kipf, P. Bloem, R. van den Berg, I. Titov, and M. Welling, “Modeling relational data with Graph Convolutional Networks,” in Proc. Extended Semantic Web Conf. (ESWC), Heraklion, Greece, Jun. 2018, pp. 593–607

2018
[27]

Hypergraph Information Bottleneck-based Implicit Semantic Communica- tion,

Y. Liao, S. Tu, Y. Zhou, Y. Xiao, Y. Li, and G. Shi, “Hypergraph Information Bottleneck-based Implicit Semantic Communica- tion,” IEEE Internet Things J., vol. 13, no. 8, pp. 15 895–15 910, 2026. 17 Yiwei Liao received his B.S. degree from the School of Electrical and Electronic engineer- ing from Huazhong University of Science and Technology, Wuhan, Chin...

2026

[1] [1]

Hypergraph reason- ing for implicit semantic-aware communication,

S. Tu, Y. Liao, Y. Xiao, Y. Li, and G. Shi, “Hypergraph reason- ing for implicit semantic-aware communication,” in Proc. IEEE Global Commun. Conf. (GLOBECOM) Workshops, Taipei, China, Dec. 2025

2025

[2] [2]

From semantic communi- cation to Semantic-Aware networking: Model, architecture, and open problems,

G. Shi, Y. Xiao, Y. Li, and X. Xie, “From semantic communi- cation to Semantic-Aware networking: Model, architecture, and open problems,” IEEE Commun. Mag., vol. 59, no. 8, pp. 44–50, Aug. 2021

2021

[3] [3]

SANet: A semantic-aware agentic AI networking framework for cross-layer optimization in 6G,

Y. Xiao, X. Li, H. Zhou, Y. Gao, G. Shi, P. Zhang, and M. Krunz, “SANet: A semantic-aware agentic AI networking framework for cross-layer optimization in 6G,” IEEE Trans. Mobile Comput., 2026

2026

[4] [4]

An introduction to semantic communica- tion and Semantic-Aware networking standardization for 6G,

G. Shi and Y. Xiao, “An introduction to semantic communica- tion and Semantic-Aware networking standardization for 6G,” GetMobile: Mobile Comput. and Commun., vol. 28, no. 3, pp. 14–19, Oct. 2024

2024

[5] [5]

SANSee: A physical-layer semantic-aware networking framework for distributed wireless sensing,

H. Zhu, Y. Xiao, Y. Li, G. Shi, and M. Krunz, “SANSee: A physical-layer semantic-aware networking framework for distributed wireless sensing,” IEEE Trans. Mobile Comput., vol. 24, no. 3, pp. 1636–1653, Mar. 2025

2025

[6] [6]

Reasoning over the air: A Reasoning-Based Implicit Semantic-Aware Communication framework,

Y. Xiao, Y. Liao, Y. Li, G. Shi, H. V. Poor, W. Saad, M. Debbah, and M. Bennis, “Reasoning over the air: A Reasoning-Based Implicit Semantic-Aware Communication framework,” IEEE Trans. Wireless Commun., vol. 23, no. 4, pp. 3839–3855, Apr. 2024

2024

[7] [7]

Imitation Learning-based Implicit Semantic-aware Communication Net- works: Multi-layer Representation and Collaborative Reason- ing,

Y. Xiao, Z. Sun, G. Shi, and D. Niyato, “Imitation Learning-based Implicit Semantic-aware Communication Net- works: Multi-layer Representation and Collaborative Reason- ing,” IEEE J. Sel. Areas Commun., vol. 41, no. 3, pp. 639–658, Mar. 2023

2023

[8] [8]

Joint Source–Channel Coding: Fundamentals and recent progress in practical designs,

D. Gunduz et al., “Joint Source–Channel Coding: Fundamentals and recent progress in practical designs,” Proc. IEEE, pp. 1–32, 2024

2024

[9] [9]

Implicit semantic communication based on Bayesian reconstruction framework,

Y. Liao, S. Tu, Y. Zhou, D. Jin, Y. Xiao, and Y. Li, “Implicit semantic communication based on Bayesian reconstruction framework,” IEEE Wireless Commun. Lett., vol. 15, pp. 430– 434, 2026

2026

[10] [10]

On the rep- resentation and embedding of knowledge bases beyond binary relations,

J. Wen, J. Li, Y. Mao, S. Chen, and R. Zhang, “On the rep- resentation and embedding of knowledge bases beyond binary relations,” in Proc. Int. Joint Conf. Artif. Intell. (IJCAI), New York, NY, USA, Jul. 2016, pp. 1300–1307

2016

[11] [11]

Role-aware modeling for N-ary relational knowledge bases,

Y. Liu, Q. Yao, and Y. Li, “Role-aware modeling for N-ary relational knowledge bases,” in Proc. Web Conf. 2021, New York, NY, USA, Jun. 2021, pp. 2660–2671

2021

[12] [12]

Inference of Hyperedges and overlapping communities in Hypergraphs,

M. Contisciani, F. Battiston, and C. De Bacco, “Inference of Hyperedges and overlapping communities in Hypergraphs,” Nature Commun., vol. 13, no. 1, p. 7229, Nov. 2022

2022

[13] [13]

Community detection in Hypergraphs: Optimal statistical limit and eﬀicient algorithms,

I. Chien, C.-Y. Lin, and I.-H. Wang, “Community detection in Hypergraphs: Optimal statistical limit and eﬀicient algorithms,” in Proc. Int. Conf. Artif. Intell. Statist. (AISTATS), vol. 84, Playa Blanca, Spain, Apr. 2018, pp. 871–879

2018

[14] [14]

A survey on Hypergraph Representation Learn- ing,

A. Antelmi, G. Cordasco, M. Polato, V. Scarano, C. Spagnuolo, and D. Yang, “A survey on Hypergraph Representation Learn- ing,” ACM Comput. Surv., vol. 56, no. 1, p. Art. no. 24, Aug. 2023

2023

[15] [15]

Hypergraph Learning: Methods and practices,

Y. Gao, Z. Zhang, H. Lin, X. Zhao, S. Du, and C. Zou, “Hypergraph Learning: Methods and practices,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 5, pp. 2548–2566, May 2022

2022

[16] [16]

Deeper insights into Graph Con- volutional Networks for Semi-Supervised Learning,

Q. Li, Z. Han, and X.-m. Wu, “Deeper insights into Graph Con- volutional Networks for Semi-Supervised Learning,” in Proc. AAAI Conf. Artif. Intell., vol. 32, no. 1, New Orleans, LA, USA, Apr. 2018, pp. 3538–3545

2018

[17] [17]

Not too little, not too much: A theoretical analysis of Graph (over) smoothing,

N. Keriven, “Not too little, not too much: A theoretical analysis of Graph (over) smoothing,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), New Orleans, LA, USA, Dec. 2022

2022

[18] [18]

Preventing Over- Smoothing for Hypergraph Neural Networks,

G. Chen, J. Zhang, X. Xiao, and Y. Li, “Preventing Over- Smoothing for Hypergraph Neural Networks,” arXiv preprint, 2022, arXiv:2203.17159

work page arXiv 2022

[19] [19]

Hypergraph Neural Networks,

Y. Feng, H. You, Z. Zhang, R. Ji, and Y. Gao, “Hypergraph Neural Networks,” in Proc. AAAI Conf. Artif. Intell., Honolulu, HI, USA, Jul. 2019, pp. 3558–3565

2019

[20] [20]

HGNN+: General hypergraph neural networks,

Y. Gao, Y. Feng, S. Ji, and R. Ji, “HGNN+: General hypergraph neural networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 3, pp. 3181–3199, Mar. 2023

2023

[21] [21]

Generalizing tensor decomposition for N-ary relational knowledge bases,

Y. Liu, Q. Yao, and Y. Li, “Generalizing tensor decomposition for N-ary relational knowledge bases,” in Proc. Web Conf. 2020, Taipei, China, Apr. 2020, pp. 1104–1114

2020

[22] [22]

Hyperbolic Graph Convolutional Neural Networks,

I. Chami, Z. Ying, C. Ré, and J. Leskovec, “Hyperbolic Graph Convolutional Neural Networks,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 32, Vancouver, BC, Canada, Dec. 2019

2019

[23] [23]

Knowledge Graph Embedding for Link Prediction: A compar- ative analysis,

A. Rossi, D. Barbosa, D. Firmani, A. Matinata, and P. Merialdo, “Knowledge Graph Embedding for Link Prediction: A compar- ative analysis,” ACM Trans. Knowl. Discov. Data, vol. 15, no. 2, p. Art. no. 14, Jan. 2021

2021

[24] [24]

Knowledge Graph Embedding by translating on hyperplanes,

Z. Wang, J. Zhang, J. Feng, and Z. Chen, “Knowledge Graph Embedding by translating on hyperplanes,” in Proc. AAAI Conf. Artif. Intell., Quebec City, QC, Canada, Jun. 2014, pp. 1112–1119

2014

[25] [25]

A theory of semantic communication,

Y. Shao, Q. Cao, and D. Gündüz, “A theory of semantic communication,” IEEE Transactions on Mobile Computing, vol. 23, no. 12, pp. 12 211–12 228, Dec 2024

2024

[26] [26]

Modeling relational data with Graph Convolutional Networks,

M. Schlichtkrull, T. N. Kipf, P. Bloem, R. van den Berg, I. Titov, and M. Welling, “Modeling relational data with Graph Convolutional Networks,” in Proc. Extended Semantic Web Conf. (ESWC), Heraklion, Greece, Jun. 2018, pp. 593–607

2018

[27] [27]

Hypergraph Information Bottleneck-based Implicit Semantic Communica- tion,

Y. Liao, S. Tu, Y. Zhou, Y. Xiao, Y. Li, and G. Shi, “Hypergraph Information Bottleneck-based Implicit Semantic Communica- tion,” IEEE Internet Things J., vol. 13, no. 8, pp. 15 895–15 910, 2026. 17 Yiwei Liao received his B.S. degree from the School of Electrical and Electronic engineer- ing from Huazhong University of Science and Technology, Wuhan, Chin...

2026