论文检索

Applications · Computer Vision

Mingcheng Wang, junbo qiao, Yunchen Li, Lingfu Jiang, Wei Li, Jie Hu, Jiao Xie, Zhou Yu, Xinghao Chen, Guixu Zhang 等

Speculative decoding (SD) has emerged as a key solution to accelerate the inference of autoregressive models. However, in the field of image generation, it faces the challenge of low acceptance rates, and directly relaxing its criteria leads to degradation in image quality. In this paper, we propose a novel content-aware speculative decoding algorithm, termed CSD, which integrates an entropy-based probability relaxation mechanism with an optimal resampling strategy to enhance the inference efficiency for autoregressive image generation. By leveraging the informational uncertainty inherent in different regions of an image, CSD dynamically adjusts the acceptance probability of candidate tokens, increasing the acceptance rate in low-detail areas to accelerate generation. Moreover, a distribution alignment filter is introduced to ensure the output distribution to be aligned with the target model, which significantly improves the generative quality. Experiments conducted on Lumina-mGPT and Janus-Pro demonstrate that the superiority of the proposed CSD. Our source codes are released in Supplementary Material.

General Machine Learning · Unsupervised and Semi-supervised Learning

alain rakotomamonjy, Maxime Vono, Ralaivola Liva

This work proposes a novel method for solving learning from label proportion problems. For this purpose, we learn a classifier that minimizes three key objectives: (i) a bag-level loss, which quantifies the discrepancy between true and predicted label proportions in bags, (ii) an instance-level loss, inspired from domain adaptation, which leverages anchor samples with known labels and trainable supports and (iii) a distribution discrepancy that aims at aligning anchor's learned support with those of the bag samples. The problem is formulated as an alternating optimization process, iteratively updating the classifier and aligning distributions via a particle flow method. The flow of anchor samples is governed by a vector field designed to minimize the anchor loss while ensuring alignment between anchor and bag distributions. We provide a theoretical analysis, guaranteeing the convergence of the flow and identifying conditions under which the method achieves effective alignment. Our analysis highlights that gap and diversity in label proportions within bags is a critical factor for learnability. Empirical results on tabular and image datasets demonstrate the method's effectiveness, outperforming state-of-the-art approaches.

General Machine Learning · Transfer, Multitask and Meta-learning

Hao Gu, Mao-Lin Luo, Zi-Hao Zhou, Han-Chen Zhang, Min-Ling Zhang, Tong Wei

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates, rather than considering what properties make the current task-specific update naturally preserve previously acquired knowledge. From a knowledge-decomposition perspective, we observe that low-rank adaptations exhibit highly imbalanced singular value spectra: a few dominant components absorb most of the adaptation energy, thereby (i) more likely to disrupt previously acquired knowledge and (ii) making the update more vulnerable to interference from subsequent tasks. To enable explicit balance among components, we decouple the *magnitude* of the task update from its *directional structure* and formulate it as a constrained optimization problem on a restricted Stiefel manifold. We address this problem using a projected first-order method compatible with standard deep-learning optimizers used in vision-language models. Our method mitigates both backward and forward forgetting, consistently outperforming continual learning baselines. Source code is available in supplementary material.

General Machine Learning · Transfer, Multitask and Meta-learning

Romain Cosentino

We develop a continual learning method for pretrained models that \emph{requires no access to old-task data}, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable. Our key observation is that pretrained networks exhibit substantial \emph{geometric redundancy}, and that this redundancy can be exploited in two complementary ways. First, redundant neurons provide a proxy for dominant pretraining-era feature directions, enabling the construction of approximately protected update subspaces directly from pretrained weights. Second, redundancy offers a natural bias for \emph{where} to place plasticity: by restricting updates to a subset of redundant neurons and constraining the remaining degrees of freedom, we obtain update families with reduced functional drift on the old-data distribution and improved worst-case retention guarantees. These insights lead to \textsc{PLATE} (\textbf{Pla}sticity-\textbf{T}unable \textbf{E}fficient Adapters), a continual learning method requiring no past-task data that provides explicit control over the plasticity-retention trade-off. PLATE parameterizes each layer with a structured low-rank update $\Delta W = B A Q^\top$, where $B$ and $Q$ are computed once from pretrained weights and kept frozen, and only $A$ is trained on the new task.

General Machine Learning · Transfer, Multitask and Meta-learning

Zhenyi Wang, Yixuan Sun, Yue Wang, Zhong Chen, Heng Huang

Continual learning (CL) aims to acquire new knowledge from a non-stationary data stream while retaining performance on previously learned tasks. Memory-based replay methods mitigate catastrophic forgetting by storing and revisiting past samples, but their effectiveness is fundamentally constrained by limited memory capacity, as each stored example represents only a single data instance. In this work, we propose data reassembly for CL, a new paradigm that significantly increases memory efficiency by reassembling composite replay samples from existing training data. Instead of storing raw training examples, we partition the current task training data into elementary patches and dynamically reassemble them into coherent replay instances through an energy-based optimization framework. The proposed objective jointly enforces semantic compatibility with target labels and global consistency among assembled patches. To make this optimization tractable, we derive an efficient variational inference algorithm that constructs a compact yet diverse set of reassembled samples for replay. Extensive theoretical analysis and experiments across multiple CL benchmarks demonstrate that data reassembly consistently outperforms existing memory-based approaches, achieving stronger retention of past knowledge while maintaining competitive computational efficiency.

General Machine Learning · Transfer, Multitask and Meta-learning

Binh-Nguyen Nguyen, Khang Tran, Hai Phan, Issa Khalil

Many organizations lack computational resources to fine-tune large language models (LLMs) on private (unshareable) data for better utility, while fine-tuning tiny language models (TinyLMs) alone performs poorly. To address this bottleneck, we propose a data-free knowledge distillation framework that generates LLM update vectors based on TinyLMs fine-tuned on private data. An update vector is a vector of parameter changes from an initial model to its fine-tuned version on a dataset, capturing the effect of cumulative gradient steps during fine-tuning. The key idea of our framework is a novel **Gradient Transformer** that transforms TinyLM's update vectors into LLM's update vectors. As derived from shadow datasets, $\texttt{Grad-Transformer}$ captures the correlation between TinyLM and LLM update vectors, enabling third-party providers to generate LLM update vectors given the organization's TinyLM update vectors without accessing the organization's private data. The framework supports multi-organization collaboration to jointly update LLMs, improving performance and cost-efficiency. Extensive experiments across language modeling and reasoning tasks show that $\texttt{Grad-Transformer}$ remarkably outperforms state-of-the-art knowledge distillation baselines, even under strict differential privacy protection.

Applications · Time Series

Difei Hou, Jiaqi Yue, Chunhui Zhao

Explainability is essential for applying time series analysis in high-stakes domains. While Time Series Captioning (TSC) offers a pathway to enhance temporal explainability, achieving reliable caption generation usually necessitates high-quality textual annotations. However, as interpreting abstract temporal dynamics requires specialized domain knowledge, acquiring such caption annotations is challenging, thereby impeding the advancement of TSC. To address this challenge, we introduce a novel Caption Label-Free Learning (CLFL) paradigm. Departing from the supervised learning tradition of imitating human annotations, CLFL formulates captioning as an agentic exploration task optimized by feedback from a proxy reward. Specifically, we propose a Dual Loop Agentic Captioning (DLAC) framework to achieve such an exploration-feedback mechanism. In the inner loop, a Time Series Captioning LLM Agent (TSCAgent) reflectively explores potential semantic captions. In turn, the outer loop evaluates these captions via downstream reasoning to derive a proxy reward, which feeds back to optimize the TSCAgent. Empirical results validate the effectiveness of the CLFL, proving that the exploration-feedback mechanism is sufficient for learning complex temporal semantics and autonomously generating captions, without any caption label supervision. Furthermore, we release TFTSC, an industrial expert-level time series caption dataset, which is available at: \url{https://anonymous.4open.science/r/TFTSC-05ED/}.

General Machine Learning · Transfer, Multitask and Meta-learning

Thomas Sommariva, Francesca Morandi, Simone Calderara, Angelo Porrello

Task vector composition has emerged as a promising paradigm for editing pre-trained models, enabling model merging via addition and task removal via subtraction. Fine-tuning in the tangent space of a pre-trained model (*linearized fine-tuning*) has proven particularly effective in this setting, as it yields task vectors that are naturally disentangled and less prone to interference. However, linearized models suffer from reduced expressivity during training and increased computational cost at inference time, limiting their practical applicability. In this work, we propose to bridge linearized and standard non-linear fine-tuning through knowledge distillation. Specifically, we distill hidden representations from a linearized, curvature-regularized teacher into a non-linear student trained with conventional fine-tuning. By doing so, the goal is to transfer the disentanglement properties of the linearized regime, biasing optimization toward solutions that are composable by design. We show that the resulting task vectors can be composed using naïve Task Arithmetic, achieving strong results across vision and language benchmarks without incurring any inference-time overhead.

General Machine Learning · Supervised Learning

Yunan Lu, Haitao Wu, Weiwei Li, Lei Yang, Xiuyi Jia

Label Distribution Learning (LDL) is an effective learning paradigm for predicting entire conditional label distributions, improving the trustworthiness of predictions in risk-sensitive tasks. Although previous LDL methods achieve satisfactory performance on conventional evaluation metrics, they generally overlook the divisiveness within label distributions, i.e., the propensity of label distribution to exhibit dissension between semantically opposing labels, which is an essential indicator of the practical decision risk. Therefore, we propose a divisiveness‑consistent label distribution learning framework to quantify and preserve the divisiveness information. First, we formalize a divisiveness measure that satisfies the axiomatic property of polarity monotonicity to quantify the divisiveness information. Second, we theoretically demonstrate the inconsistency between conventional loss functions and divisiveness error. Besides, in order to address the adversarial gradient problem arising from directly minimizing the divisiveness error, we propose a pairwise divisiveness loss as an unbiased estimator of the original divisiveness error. Experiments confirm the effectiveness of the proposed method.

General Machine Learning · Supervised Learning

Haitao Wu, Weiwei Li, Kun Yue, Xiuyi Jia

Label ambiguity/polysemy is pervasive in supervised learning, motivating a variety of representations beyond the traditional single-label setting. While label distribution (LD) provides a probabilistic description and has attracted increasing attention, we reveal its inherent limitations, including inconsistency with raw data, distortion of inter-sample order, and limited applicability. To address these issues, we introduce generalized label distribution (GLD), a unified representation that can perfectly recover raw data while preserving inter-sample order consistency, transform into existing forms of label representations without information loss, and capture out-of-distribution samples as well as negative label correlations. We further develop GLD learning algorithms and demonstrate their effectiveness through both theoretical analysis and extensive experiments.

General Machine Learning · Supervised Learning

Jiacheng Cui, Bingkui Tong, Xinyue Bi, Xiaohan Zhao, Jiacheng Liu, Zhiqiang Shen

Soft labels from teacher models are a $\textit{de facto}$ practice for knowledge transfer and large-scale dataset distillation (e.g., SRe$^2$L, RDED, LPLD). However, when we limit the number of crops per image to reduce the substantial cost of storing precomputed soft labels, these methods suffer severely from $\textit{local semantic drift}$: visually ambiguous crops can cause soft supervision to deviate from the image-level ground-truth semantics, leading to systematic errors and a train–test distribution mismatch. We revisit the overlooked role of hard labels and show that, when properly integrated, they act as a content-agnostic semantic anchor that calibrates such drift. We theoretically analyze the emergence of drift under sparse soft-label supervision and demonstrate that hybridizing hard and soft labels restores alignment between visual content and semantic supervision. Building on this insight, we propose a new training paradigm, $\textbf{H}$ard Label for $\textbf{A}$lleviating $\textbf{L}$ocal Semantic $\textbf{D}$rift (HALD), which uses hard labels as intermediate corrective signals while preserving the fine-grained benefits of soft labels. Extensive experiments on dataset distillation and large-scale classification benchmarks show consistent generalization improvements. On ImageNet-1K, our method achieves 42.7% accuracy with only 285M soft-label storage (reduces by ${\bf 100\times})$, outperforming prior state-of-the-art LPLD by 9.0%.

Optimization · Stochastic

Fabian Schaipp, Robert Gower, Adrien Taylor

We present a theoretical analysis of stochastic optimization methods in terms of their sensitivity with respect to the step size. We identify a key quantity that, for each method, describes how the performance degrades as the step size becomes too large. For convex problems, we show that this quantity directly impacts the suboptimality bound of the method. Most importantly, our analysis provides direct *theoretical* evidence that adaptive step size methods, such as SPS or NGN, are more robust than SGD. This allows us to quantify the advantage of these adaptive methods beyond empirical evaluation. Finally, we show through experiments that our theoretical bound qualitatively mirrors the actual performance as a function of the step size, even for nonconvex problems.

General Machine Learning · Supervised Learning

Zhuang Qi, Yingpeng Tang, Lei Meng, Xiaoxiao Li, Han Yu, Xiangxu Meng

Federated Class-Incremental Learning (FCIL) aims to continually expand a model’s recognition capacity in a distributed environment, enabling it to learn new classes while retaining knowledge of previously seen ones. Exemplar replay has emerged as a promising strategy owing to its simplicity and effectiveness. Existing methods either select exemplars based on local dynamics or construct global feature spaces to identify representative samples. However, they face inherent challenges in striking a balance between effectiveness and privacy. To address this issue, this paper proposes a Cross-view Lewis weIght Fusion method for exemplar replay in FCIL, termed CLIF, which fuses multi-view importance scores to guide representative sample selection under federated settings. Specifically, CLIF consists of two main modules: 1) the cross-view Lewis weight fusion module computes and integrates Lewis weights from multiple feature perspectives to achieve consistent importance estimation, ensuring that the selected samples better reflect the global data distribution and thus enhancing the representativeness of the replay subset. Building on this, 2) the frequency-based weighted training module adjusts the loss contribution of each sample according to its selection frequency across views, which emphasizes the contribution of critical samples. Moreover, we provide a theoretical analysis to guarantee the soundness and effectiveness of CLIF. Extensive experiments on three datasets demonstrate that our method consistently improves baselines by 1%–6%, supporting the above claims.

General Machine Learning · Representation Learning

Chaewon Lee, BeomJun Shim, Kwang Choi, Chang-Su Kim

We propose contrastive order learning (ConOrd), a contrastive learning framework for ordinal regression that integrates the strengths of contrastive learning and order learning. While contrastive learning effectively leverages all samples in a batch, it typically ignores the inherent ordering among rank labels. Conversely, order learning explicitly models label ordinality but often relies on local, margin-based comparisons, limiting its ability to capture global ordinal structure. ConOrd addresses these limitations by introducing a contrastive order loss with soft affinity and disparity weights based on rank differences, enabling fine-grained modeling of ordinal relationships across all sample pairs within a batch. Extensive experiments on a range of ordinal regression tasks, including facial age estimation, blind image quality assessment, and blind video quality assessment, demonstrate that ConOrd consistently achieves state-of-the-art performance and generalizes well across diverse ordinal regression scenarios.

Deep Learning · Large Language Models

Charilaos Pipis, Shivam Garg, Vasilis Kontonis, Vaishnavi Shrivastava, Akshay Krishnamurthy, Dimitris Papailiopoulos

Reasoning models (e.g., DeepSeek-R1) generate long chains of thought to solve harder problems, but they often loop, repeating the same text at low temperatures or with greedy decoding. We study why this happens and what role temperature plays. With open reasoning models, we find that looping is common at low temperature. Larger models tend to loop less, and distilled students loop significantly even when their teachers rarely do. This points to mismatches between the training distribution and the learned model, which we refer to as errors in learning, as a key cause. To understand how such errors cause loops, we introduce a synthetic graph reasoning task and demonstrate two mechanisms. First, risk aversion caused by hardness of learning: when the correct progress-making action is hard to learn but an easy cyclic action is available, the model puts relatively more probability on the cyclic action and gets stuck. Second, even when there is no hardness, Transformers show an inductive bias toward temporally correlated errors, so the same few actions keep being chosen and loops appear. Higher temperature reduces looping by promoting exploration, but it does not fix the errors in learning, so generations remain much longer than necessary at high temperature; in this sense, temperature is a stopgap rather than a holistic solution. We end with a discussion of training-time interventions aimed at directly reducing errors in learning.

Deep Learning · Self-Supervised Learning

Dong Lao

This position paper argues that the absence of labels does not imply the absence of human supervision in visual learning, and therefore urges the research community to explicitly identify sources of supervision, rather than grouping all label-free approaches under the umbrella term "unsupervised". Many recent methods in computer vision build upon pre-trained representations learned from large-scale unlabeled data, and are therefore regarded as requiring no human supervision. We argue that this view conflates label-free learning with human-free learning, as data curation and filtering inevitably embed substantial human priors on which modern learning systems rely. This confusion risks gatekeeping fundamental unsupervised learning research, a trend reflected in the surprising decline of the term “unsupervised” in paper titles following the rise and widespread adoption of self-supervised pre-training, despite continued growth of the field. Rather than questioning the legitimacy of foundational pre-training within unsupervised learning, we advocate for greater conceptual clarity by encouraging authors to disclose data distribution priors and data-selective biases, and to specify which components of a learning pipeline depend on which assumptions. Standardized disclosure practices can improve academic communication, ensure fairer comparisons, and preserve methodological diversity in unsupervised learning.

General Machine Learning · Representation Learning

Zixuan Qin, Qi Shen, Liu Yang, Qilong Wang, Qinghua Hu

Federated learning often face both data and model heterogeneity, with the latter often more challenging. Architectural differences yield incompatible representation, making the knowledge-sharing carrier central to heterogeneous collaboration. Using proxy model enables distillation-based collaboration but incurs high communication and computation costs. Prototype-based carriers are lighter yet cause semantic confusion when incompatible features are mixed. Therefore, we propose rule-based federated learning (RFL) that shares interpretable, class-discriminative rules to enable heterogeneous collaboration, avoid feature confusion, and keep communication lightweight. RFL uses a rule network to unify clients’ decision features and collaborates at the rule level, avoiding forcible averaging of incompatible representations. RFL selects sparse, high-coverage, beneficial rules for broadcasting, compressing shared knowledge into an interpretable class-rule set and reducing communication and computation costs. Each client selectively activates only rules relevant to its local classes, mitigating negative transfer while preserving personalization. Across heterogeneous settings, RFL achieves a better accuracy–communication trade-off.

Applications · Health / Medicine

Qiang Zhou, Hanzhen Zhu, Pan Wang, Rui Tu, Huaizhi Qu, Zhuoran Wang, Xin Hu, Lei Li, Tianlong Chen, Jingtong Hu

According to the reformulated version of the Learned Helplessness theory, an individual who experiences uncontrollable negative events may subsequently develop a negative attributional style, thereby exhibiting greater susceptibility to depressive symptoms. This depressogenic attributional style not only contributes to depressive symptoms but also represents a malleable target for cognitive therapy. Despite its theoretical and practical significance, computational research on attributional cognition remains underexplored due to the lack of large-scale, high-quality datasets and robust evaluation protocols. In this work, we introduce the Attributional Style Transfer Dataset (ASTD) along with dedicated evaluation metrics, the first benchmark designed to model, assess, and reframe attributional explanations at scale. Constructed via a Prevent–Filter–Validate pipeline that integrates LLM-based generation with specialist validation, ASTD contains 42,000 real-world events paired with psychologically grounded attributions spanning seven styles. Using this dataset, we address two key challenges: (1) scalable assessment of attributional style via both supervised classifiers and zero/few-shot LLMs; and (2)attributional reframing and evaluation, where we propose automatic evaluation metrics to quantify psychological validity. Furthermore, we leverage our proposed metrics to construct a preference dataset, fine-tuning LLMs with Direct Preference Optimization (DPO) and achieving substantial gains in reframing quality. Together, our dataset, metrics, and methodology offer a new paradigm for understanding and modeling attributional style, with direct implications for scalable and adaptive mental health interventions.

General Machine Learning · Representation Learning

Alexandre Chaussard, Anna Bonnet, Sylvain Le Corff

Advances in data collection are producing growing volumes of temporal count observations, making adapted modeling increasingly necessary. In this work, we introduce a generative framework for independent component analysis of temporal count data, combining regime-adaptive dynamics with Poisson log-normal emissions. The model identifies disentangled components with regime-dependent contributions, enabling representation learning and perturbations analysis. Notably, we establish the identifiability of the model, supporting principled interpretation. To learn the parameters, we propose an efficient amortized variational inference procedure. Experiments on simulated data evaluate recovery of the mixing function and latent sources across diverse settings, while an *in vivo* longitudinal gut microbiome study reveals microbial co-variation patterns and regime shifts consistent with clinical perturbations.

General Machine Learning · Representation Learning

Kirill Shevkunov, Andrey Ploskonosov, Liudmila Prokhorenkova

In many machine learning applications, the most relevant items for a query should be efficiently extracted. The relevance function is usually an expensive similarity model making the exhaustive search infeasible. A typical solution is to train another model that separately embeds queries and items to a vector space, where similarity is defined via the dot product or cosine similarity. This allows one to search the relevant items through fast approximate nearest neighbors search at the cost of some reduction in quality. To compensate for this reduction, the found items (candidates) are re-ranked by the expensive ranking model. In this paper, we investigate an alternative approach to candidate selection that utilizes the scores of the expensive model to improve the representations of queries and items. The idea is to describe each query (item) by its relevance for a set of support items (queries) and use these new representations to obtain query (item) embeddings. We theoretically prove that such embeddings are powerful enough to approximate any complex similarity model (under mild conditions). We also investigate the choice of support items, which is a crucial ingredient of the proposed approach. The experiments on diverse academic and production datasets illustrate the power of our method.