Optimize Incompatible Parameters through Compatibility-aware Knowledge Integration

• URL: http://arxiv.org/abs/2501.07596v1
• Date: Fri, 10 Jan 2025 01:42:43 GMT
• Title: Optimize Incompatible Parameters through Compatibility-aware Knowledge Integration
• Authors: Zheqi Lv, Keming Ye, Zishu Wei, Qi Tian, Shengyu Zhang, Wenqiao Zhang, Wenjie Wang, Kun Kuang, Tat-Seng Chua, Fei Wu,
• Abstract summary: Existing research excels in removing such parameters or merging the outputs of multiple different pretrained models.<n>We propose Compatibility-aware Knowledge Integration (CKI), which consists of Deep Assessment and Deep Splicing.<n>The integrated model can be used directly for inference or for further fine-tuning.
• Score: 104.52015641099828
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks have become foundational to advancements in multiple domains, including recommendation systems, natural language processing, and so on. Despite their successes, these models often contain incompatible parameters that can be underutilized or detrimental to model performance, particularly when faced with specific, varying data distributions. Existing research excels in removing such parameters or merging the outputs of multiple different pretrained models. However, the former focuses on efficiency rather than performance, while the latter requires several times more computing and storage resources to support inference. In this paper, we set the goal to explicitly improve these incompatible parameters by leveraging the complementary strengths of different models, thereby directly enhancing the models without any additional parameters. Specifically, we propose Compatibility-aware Knowledge Integration (CKI), which consists of Parameter Compatibility Assessment and Parameter Splicing, which are used to evaluate the knowledge content of multiple models and integrate the knowledge into one model, respectively. The integrated model can be used directly for inference or for further fine-tuning. We conduct extensive experiments on various datasets for recommendation and language tasks, and the results show that Compatibility-aware Knowledge Integration can effectively optimize incompatible parameters under multiple tasks and settings to break through the training limit of the original model without increasing the inference cost.

Related papers

• Dynamic Fisher-weighted Model Merging via Bayesian Optimization [37.02810891820468]
  Existing merging approaches typically involve scaling the parameters model-wise or integrating parameter importance parameter-wise. We unify these strategies into a more general merging framework, and introduce Dynamic Fisher-weighted Merging (DF-Merge) We show that DF-Merge outperforms strong baselines across models of different sizes and a variety of tasks.
  arXiv  Detail & Related papers  (2025-04-26T18:31:14Z)
• Model Assembly Learning with Heterogeneous Layer Weight Merging [57.8462476398611]
  We introduce Model Assembly Learning (MAL), a novel paradigm for model merging. MAL integrates parameters from diverse models in an open-ended model zoo to enhance the base model's capabilities.
  arXiv  Detail & Related papers  (2025-03-27T16:21:53Z)
• Parameter Efficient Merging for Multimodal Large Language Models with Complementary Parameter Adaptation [17.39117429338763]
  We propose CoPA-Merging, a training-free parameter efficient merging method with complementary parameter adaptation. We establish a benchmark consisting of diverse multimodal tasks, on which we conduct experiments to certificate the outstanding performance and generalizability of our method.
  arXiv  Detail & Related papers  (2025-02-24T13:52:05Z)
• Mitigating Parameter Degeneracy using Joint Conditional Diffusion Model for WECC Composite Load Model in Power Systems [2.7212274374272543]
  We develop a joint conditional diffusion model-based inverse problem solver (JCDI) JCDI incorporates a joint conditioning architecture with simultaneous inputs of multi-event observations to improve parameter generalizability. Simulation studies on the WECC CLM show that the proposed JCDI effectively reduces uncertainties of degenerate parameters.
  arXiv  Detail & Related papers  (2024-11-15T18:53:08Z)
• Parameter Competition Balancing for Model Merging [13.66727853299506]
  PCB-Merging is a training-free technique that adjusts the coefficients of each parameter for effective model merging. PCB-Merging achieves substantial performance enhancements across multiple modalities, domains, model sizes, number of tasks, fine-tuning forms, and large language models.
  arXiv  Detail & Related papers  (2024-10-03T11:17:58Z)
• Self-Updatable Large Language Models with Parameter Integration [21.742149718161716]
  Small-scale experiences, such as interactions with surrounding objects, require frequent integration in large language models. Current methods embed experiences within model parameters using continual learning, model editing, or knowledge distillation techniques. We propose SELF-PARAM, which embeds experiences directly into model parameters and ensures near-optimal efficacy and long-term retention.
  arXiv  Detail & Related papers  (2024-10-01T08:18:17Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• Fairer and More Accurate Tabular Models Through NAS [14.147928131445852]
  We propose using multi-objective Neural Architecture Search (NAS) and Hyperparameter Optimization (HPO) in the first application to the very challenging domain of tabular data. We show that models optimized solely for accuracy with NAS often fail to inherently address fairness concerns. We produce architectures that consistently dominate state-of-the-art bias mitigation methods either in fairness, accuracy or both.
  arXiv  Detail & Related papers  (2023-10-18T17:56:24Z)
• Switchable Representation Learning Framework with Self-compatibility [50.48336074436792]
  We propose a Switchable representation learning Framework with Self-Compatibility (SFSC) SFSC generates a series of compatible sub-models with different capacities through one training process. SFSC achieves state-of-the-art performance on the evaluated datasets.
  arXiv  Detail & Related papers  (2022-06-16T16:46:32Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)
• On the Parameter Combinations That Matter and on Those That do Not [0.0]
  We present a data-driven approach to characterizing nonidentifiability of a model's parameters. By employing Diffusion Maps and their extensions, we discover the minimal combinations of parameters required to characterize the dynamic output behavior.
  arXiv  Detail & Related papers  (2021-10-13T13:46:23Z)

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.