论文检索

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.

Applications · Time Series

Yu Fan, Yang Yang, Yufan Guo, Huazhong Yang, pengjun wang

Real-world time-series data often suffer from missing observations, hindering long-range temporal modeling. However, most existing imputation methods formulate imputation as conditional reconstruction over limited context, which restricts temporal information propagation and fails to explicitly model temporal evolution. To overcome this limitation, we propose the Conditional Temporal Inference Paradigm (CTIP), which formulates time-series imputation as conditional inference along temporal evolution. Under this paradigm, we introduce CBiT, which leverages a history compression mechanism to encode long-range history into a compact latent space for history-conditioned temporal imputation. In addition, we adopt a partitioned modeling strategy that distinguishes historical context and temporal imputation targets with only linear-time complexity. Extensive experiments on multiple public benchmarks show that CBiT improves imputation accuracy by reducing Masked MAE and Masked RMSE by 27.3% and 18.6%, respectively, across different missing rates.

General Machine Learning · Hardware and Software

Qinhong Ma, Yulin Chen, Zhiwei Fan, Suzhen Wu, Bo Mao

Weightless Neural Networks (WNNs) based on interconnected Lookup Tables (LUTs) have attracted attention for inference in extremely compact models, but achieving competitive accuracy under such tight resource budgets remains challenging. To address these issues, we introduce the Convolutional Learnable-Group Weightless Neural Network (CLGN). CLGN constructs convolutional layers using LUTs and incorporates a learnable GroupSum connection, thereby enhancing the accuracy of WNNs while maintaining low implementation resource consumption. Moreover, we propose a hierarchical training strategy to improve the training efficiency. We evaluate CLGN in two edge computing scenarios: (1) FPGA, where we evaluate accuracy, latency, throughput, power consumption, LUTs usage, and parameter size; and (2) Microprocessor, where we evaluate latency and memory usage. Compared with the state-of-the-art solutions, the proposed CLGN achieves superior accuracy while maintaining lower implementation resource consumption.

General Machine Learning · Hardware and Software

Anselm Paulus, Andreas René Geist, Vit Musil, Sebastian Hoffmann, Georg Martius

Automatic differentiation (AD) frameworks such as JAX and PyTorch have enabled gradient-based optimization for a wide range of scientific fields. Yet, many ''hard'' primitives in these libraries such as thresholding, Boolean logic, discrete indexing, and sorting operations yield zero or undefined gradients that are not useful for optimization. While numerous ''soft'' relaxations have been proposed that provide informative gradients, the respective implementations are fragmented across projects, making them difficult to combine and compare. This work introduces **SoftJAX** and **SoftTorch**, open-source, feature-complete libraries for *soft differentiable programming*. These libraries provide a variety of soft functions as drop-in replacements for their hard JAX and PyTorch counterparts. This includes (i) elementwise operators such as *clip* or *abs*, (ii) utility methods for manipulating Booleans and indices via fuzzy logic, (iii) axiswise operators such as *sort* or *rank* -- based on optimal transport or permutahedron projections, and (iv) offer full support for straight-through gradient estimation. Overall, SoftJAX and SoftTorch make the toolbox of soft relaxations easily accessible to differentiable programming, as demonstrated through benchmarking and a practical case study.

General Machine Learning · Evaluation

Alex Thillen, Niels Mündler, Veselin Raychev, Martin Vechev

Large language model (LLM)-based coding agents can generate working code, but their solutions often introduce complexity, duplication, and architectural debt. Human developers address such issues through refactoring: behavior-preserving program transformations that improve structure and maintainability. In this paper, we investigate if LLM agents (i) can execute refactorings reliably and (ii) identify refactorings that human developers chose in real codebases. We present CodeTaste, a benchmark of refactoring tasks mined from large-scale multi-file changes in open-source repositories. To score solutions, we combine repository test suites with custom static checks that verify removal of undesired code patterns and introduction of desired patterns using dataflow reasoning. Our experimental results indicate a clear gap across frontier models: agents perform well when refactorings are specified in detail, but often fail to discover the human refactoring choices when only presented with a focus area for improvement. A propose-then-implement decomposition improves alignment, and selecting the best-aligned proposal before implementation yields further gains. CodeTaste provides an evaluation target and a potential preference signal for aligning coding agents with human refactoring decisions in realistic codebases.

General Machine Learning · Evaluation

Guiyao Tie, Tianyao Luo, Xueyang Zhou, Chaoran Hu, Yunhong He, Junran Wu, Yuanfan Yao, Pan Zhou, Lichao Sun

Large language models (LLMs) are increasingly used to provide automated assessment signals for evaluating model-generated outputs. However, practical deployment faces three persistent challenges: heterogeneous reliability across models, substantial latency and token costs, and the absence of principled strategies for allocating evaluation resources. We introduce R$^2$Eval, a routing-aware automated assessment framework that formulates evaluation as a resource allocation and aggregation problem rather than relying on a single monolithic evaluator. R$^2$Eval combines difficulty-aware routing with reasoned evaluation signals to dynamically select evaluator models on a per-instance basis under explicit accuracy, latency, and cost constraints. Our study makes three contributions. First, we construct six difficulty-aware datasets spanning both reasoning-intensive (mathematics, logic, code) and non-reasoning (knowledge, roleplay, writing) tasks, with human-annotated reference assessments. Second, we provide a systematic empirical analysis of how reasoning traces produced by different evaluator models correlate with assessment outcomes, revealing substantial variance and systematic mismatches across difficulty regimes. Third, we develop and evaluate both offline and online routing strategies that adaptively allocate evaluation queries, achieving substantially improved accuracy–efficiency trade-offs compared to static baselines. Experiments across 19 language models demonstrate that R$^2$Eval significantly reduces evaluation cost and latency while maintaining close alignment with human assessments. These results highlight the importance of routing-aware automated assessment and establish R$^2$Eval as a scalable and reliable framework for large-scale model evaluation.

General Machine Learning · Evaluation

Zhengshuyuan Tian, Chuanxin Lan, Chenxi Wang, Lei Wang, Guoxin Kang, Zhengxin Yang, Yunyou Huang, Xuehai Hong, Wanling Gao, Jianfeng Zhan

Current LLM evaluations often conflate benchmark performance with intrinsic model capability. This is misleading, as observed outcomes arise from the entire evaluation system, including datasets, prompting methods, decoding parameters, and the software–hardware stack, rather than the model alone. When this system is underspecified, attribution becomes unreliable; in practice, evaluation choices alone can induce accuracy swings of up to 70\%. This attribution challenge is compounded by the open-ended nature of LLM evaluation. Questions span languages, domains, and usage styles, forming highly variable and implicitly shifting datasets. Consequently, strong performance on static benchmarks may reflect alignment with surface patterns rather than robust underlying capability. Prior studies either focus on individual components, overlooking their interactions, or investigate manually curated and small-scale question variants, lacking a holistic perspective, precluding precise attribution of intrinsic model capabilities amidst the confounding influences. To address these limitations, we propose LLM evaluatology, a principled framework that grounds LLM evaluation in a causally informed system design. By jointly modeling evaluation components and structured question variations, it enables interpretable, reproducible, and causally faithful assessment of model capability, establishing clear conditions under which evaluation results are meaningful and trustworthy.

Applications · Language, Speech and Dialog

Hang Gao, Dimitris Metaxas

GraphRAG is increasingly adopted for converting unstructured corpora into graph structures to enable multi-hop reasoning. However, standard graph algorithms rely heavily on static connectivity and explicit edges, often failing in real-world scenarios where knowledge graphs (KGs) are noisy, sparse, or incomplete. To address this limitation, we introduce INSES (Intelligent Navigation and Similarity Enhanced Search), a dynamic framework designed to reason beyond explicit edges. INSES couples LLM-guided navigation, which prunes noise and steers exploration, with embedding-based similarity expansion to recover hidden links and bridge semantic gaps. Recognizing the computational cost of graph reasoning, we complement INSES with a lightweight router that delegates simple queries to Naïve RAG and escalates complex cases to INSES, balancing efficiency with reasoning depth. INSES consistently outperforms SOTA RAG and GraphRAG baselines across multiple benchmarks. Notably, on the MINE benchmark, it demonstrates superior robustness across KGs constructed by varying methods (KGGEN, GraphRAG, OpenIE), improving accuracy by 5\%, 10\%, and 27\%, respectively.