Batch Model Consolidation: A Multi-Task Model Consolidation Framework

• URL: http://arxiv.org/abs/2305.16484v1
• Date: Thu, 25 May 2023 21:33:56 GMT
• Title: Batch Model Consolidation: A Multi-Task Model Consolidation Framework
• Abstract summary: In Continual Learning (CL), a model is required to learn a stream of tasks sequentially without significant performance degradation on previously learned tasks. We propose Batch Model Consolidation ($textbfBMC$) to support more realistic CL under conditions where multiple agents are exposed to a range of tasks. Our method outperforms the next best CL approach by 70% and is the only approach that can maintain performance at the end of 71 tasks.
• Score: 14.687385545898776
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In Continual Learning (CL), a model is required to learn a stream of tasks sequentially without significant performance degradation on previously learned tasks. Current approaches fail for a long sequence of tasks from diverse domains and difficulties. Many of the existing CL approaches are difficult to apply in practice due to excessive memory cost or training time, or are tightly coupled to a single device. With the intuition derived from the widely applied mini-batch training, we propose Batch Model Consolidation ($\textbf{BMC}$) to support more realistic CL under conditions where multiple agents are exposed to a range of tasks. During a $\textit{regularization}$ phase, BMC trains multiple $\textit{expert models}$ in parallel on a set of disjoint tasks. Each expert maintains weight similarity to a $\textit{base model}$ through a $\textit{stability loss}$, and constructs a $\textit{buffer}$ from a fraction of the task's data. During the $\textit{consolidation}$ phase, we combine the learned knowledge on 'batches' of $\textit{expert models}$ using a $\textit{batched consolidation loss}$ in $\textit{memory}$ data that aggregates all buffers. We thoroughly evaluate each component of our method in an ablation study and demonstrate the effectiveness on standardized benchmark datasets Split-CIFAR-100, Tiny-ImageNet, and the Stream dataset composed of 71 image classification tasks from diverse domains and difficulties. Our method outperforms the next best CL approach by 70% and is the only approach that can maintain performance at the end of 71 tasks; Our benchmark can be accessed at https://github.com/fostiropoulos/stream_benchmark

Related papers

• Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes [70.61868608402723]
  We introduce $textbfSelf-Correcting Coupled Markov Jump Processes (SC-CMJP)<n>In conjunction with SC-CMJP, we introduce $textttCO_texttt2textttJump$, a novel training-free single-pass sampler for joint multimodal geneneration.<n>For training and evaluation purposes, we have created and will release three large-scale joint multimodal generation corpora.
  arXiv  Detail & Related papers  (2026-07-14T18:39:29Z)
• A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks [25.713629634281077]
  We propose TASTE: Task Synthesis from Tool Sequence Evolution, an automatic method that generates challenging tasks with broader tool-use coverage.<n> TASTE selects representative sequences from the pool via clustering, instantiates them into complete benchmark tasks, and refines them through difficulty evolution.<n>Our results suggest high scores on existing benchmarks often reflect saturation rather than robust task-solving ability.
  arXiv  Detail & Related papers  (2026-05-27T14:45:59Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification [38.65432183778467]
  We introduce DeltaRubric, an approach that reformulates multimodal preference evaluation as a plan-and-execute process within a single MLLM.<n>DeltaRubric operates in two steps: acting first as a $textitDisagreement Planner$, it generates a neutral, instance-specific verification checklist.<n>We formulate DeltaRubric as a multi-role reinforcement learning problem, jointly optimizing planning and verification capabilities.
  arXiv  Detail & Related papers  (2026-05-10T02:32:19Z)
• Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems [72.3575737073235]
  Multi-Agent Systems (MAS) solve complex tasks by coordinating multiple agents through.<n>Existing approaches generates either at task level or query level, but their relative costs and benefits remain unclear.<n>We show that query-level workflow generation is not always necessary, since a small set of top-K best task-level together already covers equivalent or even more queries.
  arXiv  Detail & Related papers  (2026-01-16T10:05:51Z)
• OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging [124.91183814854126]
  Model merging seeks to combine multiple expert models into a single model.<n>We introduce a benchmark for model merging research that clearly divides the tasks for MLLM training and evaluation.<n>We find that model merging offers a promising way for building improved MLLMs without requiring training data.
  arXiv  Detail & Related papers  (2025-05-26T12:23:14Z)
• Simple Semi-supervised Knowledge Distillation from Vision-Language Models via $\mathbf{\ exttt{D}}$ual-$\mathbf{\ exttt{H}}$ead $\mathbf{\ exttt{O}}$ptimization [49.2338910653152]
  Vision-constrained models (VLMs) have achieved remarkable success across diverse tasks by leveraging rich textual information with minimal labeled data.<n> Knowledge distillation (KD) offers a well-established solution to this problem; however, recent KD approaches from VLMs often involve multi-stage training or additional tuning.<n>We propose $mathbftextttDHO$ -- a simple yet effective KD framework that transfers knowledge from VLMs to compact, task-specific models in semi-language settings.
  arXiv  Detail & Related papers  (2025-05-12T15:39:51Z)
• Towards Efficient Automatic Self-Pruning of Large Language Models [55.90119819642064]
  Post-training structured pruning is a promising solution that prunes Large Language Models without the need for retraining. We argue that the key to mitigating this issue lies in accurately determining the pruning rate for each layer. We introduce $textbfSelf-Pruner$ an end-to-end automatic self-pruning framework for LLMs, which efficiently search layer-wise pruning rates.
  arXiv  Detail & Related papers  (2025-02-20T09:59:50Z)
• Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models [77.79855507792564]
  This paper revisits the implementation of $textbfL$oad-$textbfb$alancing $textbfL$oss (LBL) when training Mixture-of-Experts (MoEs) models.
  arXiv  Detail & Related papers  (2025-01-21T04:04:39Z)
• Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent [72.10987117380584]
  Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data.<n>We find existing methods discard task-specific information that, while causing conflicts, is crucial for performance.<n>Our approach consistently outperforms previous methods, achieving state-of-the-art results across diverse architectures and tasks in both vision and NLP domains.
  arXiv  Detail & Related papers  (2025-01-02T12:45:21Z)
• $M^3EL$: A Multi-task Multi-topic Dataset for Multi-modal Entity Linking [11.334577756093923]
  We propose a dataset construction pipeline and publish $M3EL$, a large-scale dataset for MEL. $M3EL$ includes 79,625 instances, covering 9 diverse multi-modal tasks, and 5 different topics. Our dataset effectively addresses these issues, and the $textitCLIP_textitND$ model fine-tuned with $M3EL$ shows a significant improvement in accuracy.
  arXiv  Detail & Related papers  (2024-10-08T10:52:23Z)
• In-Context Learning for Extreme Multi-Label Classification [29.627891261947536]
  Multi-label classification problems with thousands of classes are hard to solve with in-context learning alone. We propose a general program that defines multi-step interactions between LMs and retrievers to efficiently tackle such problems. Our solution requires no finetuning, is easily applicable to new tasks, alleviates prompt engineering, and requires only tens of labeled examples.
  arXiv  Detail & Related papers  (2024-01-22T18:09:52Z)
• Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation [45.90925587972781]
  Large Language Models (LLMs) have the ability to solve a variety of tasks, such as text summarization and mathematical questions. Due to high computational costs, the current trend is to use prompt instruction tuning to better adjust monolithic, pretrained LLMs for new -- but often individual -- downstream tasks. MoPs can simultaneously mitigate prompt training "interference" in multi-task, multi-source scenarios.
  arXiv  Detail & Related papers  (2023-10-04T14:11:12Z)
• FAMO: Fast Adaptive Multitask Optimization [48.59232177073481]
  We introduce Fast Adaptive Multitask Optimization FAMO, a dynamic weighting method that decreases task losses in a balanced way. Our results indicate that FAMO achieves comparable or superior performance to state-of-the-art gradient manipulation techniques.
  arXiv  Detail & Related papers  (2023-06-06T15:39:54Z)
• Simplifying and Understanding State Space Models with Diagonal Linear RNNs [56.33053691749856]
  This work disposes of the discretization step, and proposes a model based on vanilla Diagonal Linear RNNs. We empirically show that, despite being conceptually much simpler, $mathrmDLR$ is as performant as previously-proposed SSMs. We also characterize the expressivity of SSMs and attention-based models via a suite of $13$ synthetic sequence-to-sequence tasks.
  arXiv  Detail & Related papers  (2022-12-01T18:53:06Z)
• Data-Centric Debugging: mitigating model failures via targeted data collection [4.599792546344752]
  Deep neural networks can be unreliable in the real world when the training set does not adequately cover all the settings where they are deployed. We propose a general methodology for model debug that can systemically improve model performance on $mathcalE$ while maintaining its performance on the original test set.
  arXiv  Detail & Related papers  (2022-11-17T19:44:02Z)
• Cross-Modal Adapter for Text-Video Retrieval [91.9575196703281]
  We present a novel $textbfCross-Modal Adapter$ for parameter-efficient fine-tuning. Inspired by adapter-based methods, we adjust the pre-trained model with a few parameterization layers. It achieves superior or comparable performance compared to fully fine-tuned methods on MSR-VTT, MSVD, VATEX, ActivityNet, and DiDeMo datasets.
  arXiv  Detail & Related papers  (2022-11-17T16:15:30Z)
• DiSparse: Disentangled Sparsification for Multitask Model Compression [92.84435347164435]
  DiSparse is a simple, effective, and first-of-its-kind multitask pruning and sparse training scheme. Our experimental results demonstrate superior performance on various configurations and settings.
  arXiv  Detail & Related papers  (2022-06-09T17:57:46Z)
• vCLIMB: A Novel Video Class Incremental Learning Benchmark [53.90485760679411]
  We introduce vCLIMB, a novel video continual learning benchmark. vCLIMB is a standardized test-bed to analyze catastrophic forgetting of deep models in video continual learning. We propose a temporal consistency regularization that can be applied on top of memory-based continual learning methods.
  arXiv  Detail & Related papers  (2022-01-23T22:14:17Z)
• Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning [16.128652726698522]
  We propose Prototype Network-based cross-attention contrastive learning (ProtoCACL) to capture the rich mutual interactions between the support set and query set. Experimental results demonstrate that our ProtoCACL can outperform the state-of-the-art baseline model under both inconsistent $K$ and inconsistent $N$ settings.
  arXiv  Detail & Related papers  (2021-10-13T07:47:13Z)
• IDEAL: Independent Domain Embedding Augmentation Learning [8.376337907951012]
  We develop a novel mechanism, the independent domain embedding augmentation learning (I) method. It can simultaneously learn multiple independent embedding spaces for transformations generated by multiple data domains. Our ISOP is to existing DML techniques and can be seamlessly combined with prior DML approaches for enhanced performance.
  arXiv  Detail & Related papers  (2021-05-21T03:40:24Z)
• A No-Free-Lunch Theorem for MultiTask Learning [19.645741778058227]
  We consider a seemingly favorable classification scenario where all tasks $P_t$ share a common optimal classifier $h*,$. We show that, even though such regimes admit minimax rates accounting for both $n$ and $N$, no adaptive algorithm exists.
  arXiv  Detail & Related papers  (2020-06-29T03:03:29Z)

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.