Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking

• URL: http://arxiv.org/abs/2607.21426v1
• Date: Thu, 23 Jul 2026 15:29:39 GMT
• Title: Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
• Abstract summary: We propose a semantic-aware task clustering method for CMT-SemCom.<n>We show that the proposed framework effectively mitigates destructive cooperation and negative transfer.
• Score: 6.198237241838558
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cooperative multi-task semantic communication (CMT-SemCom) improves task execution performance by leveraging shared representations. However, as we demonstrated in [1], cooperative multi-tasking can be either constructive or destructive, depending on the semantic relationships among tasks. To ensure constructive cooperation, we propose a semantic-aware task clustering method for CMT-SemCom. We have formulated a sequential multi-stage optimization problem in which semantically aligned tasks are clustered once after a short initial training phase, and then end-to-end (E2E) joint training is conducted exclusively within the discovered groups. Specifically, the problem decomposes into two stages: (i) a semantic clustering problem leveraging hierarchical density-based spatial clustering, and (ii) an intra-cluster E2E CMT-SemCom learning problem. Simulation results demonstrate that the proposed framework effectively mitigates destructive cooperation and negative transfer, yielding accuracy gains compared to unclustered multi-tasking and individual training baselines.

Related papers

• Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks [4.610618579893945]
  MultiTask semantic communication (SemCom) prioritizes simultaneous execution of multiple tasks over bit-accurate reconstruction in future networks.<n>CMT-SemCom has been evaluated on homogeneous classification tasks on simplistic datasets.<n>We extend our CMT-SemCom to jointly handle heterogeneous classification and regression tasks on the complex City dataset.
  arXiv  Detail & Related papers  (2026-09-03T15:13:25Z)
• Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs [52.26652574704317]
  Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes.<n>We introduce Language Agent Teams for Task Evolution (LATTE), a framework for coordinating LLM teams inspired by distributed systems.
  arXiv  Detail & Related papers  (2026-05-07T14:19:17Z)
• Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning [58.90602461025722]
  Multi-task instruct-tuning in large language models (LLMs) has been largely driven by multi-task instruct-tuning.<n>The training paradigm suffers from a key issue, named cross-task interference, due to conflicting gradients over shared parameters among different tasks.<n>We propose BADIT that decomposes LLM parameters into high-singular-value LoRA experts representing basic abilities.<n>We conduct extensive experiments on the SuperNI benchmark with 6 LLMs, and empirical results demonstrate that BADIT can outperform SOTA methods and mitigate the degree of cross-task interference.
  arXiv  Detail & Related papers  (2026-05-07T05:08:58Z)
• CoAction: Cross-task Correlation-aware Pareto Set Learning [9.837762929043649]
  We propose a cross-tAsk correlation-aware framework for multi-objective multitask optimization.<n>By assigning task-specific embedding vectors to individual tasks, the model effectively distinguishes between tasks while facilitating knowledge sharing.<n>The proposed approach is evaluated on comprehensive multitask test suites covering both benchmark problems and real-world applications.
  arXiv  Detail & Related papers  (2026-05-03T04:52:44Z)
• Robust multi-task boosting using clustering and local ensembling [6.920276126310231]
  We propose Robust Multi-Task Boosting using Clustering and Local Ensembling (RMB-CLE)<n>RMB-CLE derives inter-task similarity directly from cross-task errors.<n>Within each cluster, a local ensemble enables robust knowledge sharing.
  arXiv  Detail & Related papers  (2026-02-15T16:59:23Z)
• Semantic-Aware Task Clustering for Federated Cooperative Multi-Task Semantic Communication [6.198237241838558]
  Task-oriented semantic communication (SemCom) prioritizes task execution over accurate symbol reconstruction.<n>We extend our CMT-SemCom framework to distributed settings by proposing a federated learning (FL) based CMT-SemCom.<n>We propose a semantic-aware task clustering method integrated in the FL process to ensure constructive cooperation.
  arXiv  Detail & Related papers  (2026-01-24T11:41:00Z)
• MEJO: MLLM-Engaged Surgical Triplet Recognition via Inter- and Intra-Task Joint Optimization [52.149337961205624]
  We propose a framework that empowers both inter- and intra-task optimization for surgical triplet recognition.<n>For inter-task optimization, we introduce the Shared-Specific-Disentangled (S$2$D) learning scheme that decomposes representations into task-shared and task-specific components.<n>For intra-task optimization conflicts, we develop a Coordinated Gradient Learning (CGL) strategy, which dissects and rebalances the positive-negative ambiguities.
  arXiv  Detail & Related papers  (2025-09-16T09:48:52Z)
• Semisoft Task Clustering for Multi-Task Learning [2.806911268410107]
  Multi-task learning (MTL) aims to improve the performance of multiple related prediction tasks by leveraging useful information from them. We propose a semisoft task clustering approach, which can simultaneously reveal the task clustering structure for both pure mixed tasks as well as select the relevant features. The experimental results based on synthetic and real-world datasets validate the effectiveness and efficiency of the proposed approach.
  arXiv  Detail & Related papers  (2022-11-28T07:23:56Z)
• Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth [83.94528876742096]
  We tackle the MTL problem of two dense tasks, ie, semantic segmentation and depth estimation, and present a novel attention module called Cross-Channel Attention Module (CCAM) In a true symbiotic spirit, we then formulate a novel data augmentation for the semantic segmentation task using predicted depth called AffineMix, and a simple depth augmentation using predicted semantics called ColorAug. Finally, we validate the performance gain of the proposed method on the Cityscapes dataset, which helps us achieve state-of-the-art results for a semi-supervised joint model based on depth and semantic
  arXiv  Detail & Related papers  (2022-06-21T17:40:55Z)
• Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation [87.1188556802942]
  We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. We propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions. Furthermore, we propose an Iterative Self-Learning (ISL) training scheme, which exploits semantic pseudo-labels to provide extra supervision on the target domain.
  arXiv  Detail & Related papers  (2021-05-17T13:42:09Z)
• Task-Feature Collaborative Learning with Application to Personalized Attribute Prediction [166.87111665908333]
  We propose a novel multi-task learning method called Task-Feature Collaborative Learning (TFCL) Specifically, we first propose a base model with a heterogeneous block-diagonal structure regularizer to leverage the collaborative grouping of features and tasks. As a practical extension, we extend the base model by allowing overlapping features and differentiating the hard tasks.
  arXiv  Detail & Related papers  (2020-04-29T02:32:04Z)

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.