Selecting input features of top relevance has become a popular method for building self-explaining models. In this work, we extend this selective rationalization approach to text matching, where the goal is to jointly select and align text pieces, such as tokens or sentences, as a justification for the downstream prediction. Our approach employs optimal transport (OT) to find a minimal cost alignment between the inputs. However, directly applying OT often produces dense and therefore uninterpretable alignments. To overcome this limitation, we introduce novel constrained variants of the OT problem that result in highly sparse alignments with controllable sparsity. Our model is end-to-end differentiable using the Sinkhorn algorithm for OT and can be trained without any alignment annotations. We evaluate our model on the StackExchange, MultiNews, e-SNLI, and MultiRC datasets. Our model achieves very sparse rationale selections with high fidelity while preserving prediction accuracy compared to strong attention baseline models.
Recent advances in deep neural networks (DNNs) owe their success to training algorithms that use backpropagation and gradient-descent. Backpropagation, while highly effective on von Neumann architectures, becomes inefficient when scaling to large networks. Commonly referred to as the weight transport problem, each neuron's dependence on the weights and errors located deeper in the network require exhaustive data movement which presents a key problem in enhancing the performance and energy-efficiency of machine-learning hardware. In this work, we propose a bio-plausible alternative to backpropa…
National University of Singapore（新加坡国立大学）；MIT（麻省理工学院）
Motivated by cutting-edge applications like cryo-electron microscopy (cryo-EM), the Multi-Reference Alignment (MRA) model entails the learning of an unknown signal from repeated measurements of its images under the latent action of a group of isometries and additive noise of magnitude $σ$. Despite significant interest, a clear picture for understanding rates of estimation in this model has emerged only recently, particularly in the high-noise regime $σ\gg 1$ that is highly relevant in applications. Recent investigations have revealed a remarkable asymptotic sample complexity of order $σ^6$ for…
The current best practice for computing optimal transport (OT) is via entropy regularization and Sinkhorn iterations. This algorithm runs in quadratic time as it requires the full pairwise cost matrix, which is prohibitively expensive for large sets of objects. In this work we propose two effective log-linear time approximations of the cost matrix: First, a sparse approximation based on locality-sensitive hashing (LSH) and, second, a Nyström approximation with LSH-based sparse corrections, which we call locally corrected Nyström (LCN). These approximations enable general log-linear time algori…
Sequence-to-sequence models are a powerful workhorse of NLP. Most variants employ a softmax transformation in both their attention mechanism and output layer, leading to dense alignments and strictly positive output probabilities. This density is wasteful, making models less interpretable and assigning probability mass to many implausible outputs. In this paper, we propose sparse sequence-to-sequence models, rooted in a new family of $α$-entmax transformations, which includes softmax and sparsemax as particular cases, and is sparse for any $α> 1$. We provide fast algorithms to evaluate these t…
Guangdong University of Technology（广东工业大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Pazhou Lab（琶洲实验室）
Domain adaptation on time series data is an important but challenging task. Most of the existing works in this area are based on the learning of the domain-invariant representation of the data with the help of restrictions like MMD. However, such extraction of the domain-invariant representation is a non-trivial task for time series data, due to the complex dependence among the timestamps. In detail, in the fully dependent time series, a small change of the time lags or the offsets may lead to difficulty in the domain invariant extraction. Fortunately, the stability of the causality inspired u…
University of Florida（佛罗里达大学）；Rice University（莱斯大学）
Graph signal processing (GSP) provides a powerful framework for analyzing signals arising in a variety of domains. In many applications of GSP, multiple network structures are available, each of which captures different aspects of the same underlying phenomenon. To integrate these different data sources, graph alignment techniques attempt to find the best correspondence between vertices of two graphs. We consider a generalization of this problem, where there is no natural one-to-one mapping between vertices, but where there is correspondence between the community structures of each graph. Beca…
Guangdong University of Technology（广东工业大学）；Peng Cheng Laboratory（鹏城实验室）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Domain adaptation on time-series data is often encountered in the industry but received limited attention in academia. Most of the existing domain adaptation methods for time-series data borrow the ideas from the existing methods for non-time series data to extract the domain-invariant representation. However, two peculiar difficulties to time-series data have not been solved. 1) It is not a trivial task to model the domain-invariant and complex dependence among different timestamps. 2) The domain-variant information is important but how to leverage them is almost underexploited. Fortunately, …
Instituto de Telecomunicações（电信研究所）；Instituto Superior Técnico, University of Lisbon（里斯本大学高等技术学院）；Unbabel
Structured prediction requires manipulating a large number of combinatorial structures, e.g., dependency trees or alignments, either as latent or output variables. Recently, the SparseMAP method has been proposed as a differentiable, sparse alternative to maximum a posteriori (MAP) and marginal inference. SparseMAP returns a combination of a small number of structures, a desirable property in some downstream applications. However, SparseMAP requires a tractable MAP inference oracle. This excludes, e.g., loopy graphical models or factor graphs with logic constraints, which generally require app…
Instituto de Telecomunicações（葡萄牙电信研究所）；Instituto Superior Técnico（高等理工学院）；Unbabel（Unbabel公司）
Selective rationalization aims to produce decisions along with rationales (e.g., text highlights or word alignments between two sentences). Commonly, rationales are modeled as stochastic binary masks, requiring sampling-based gradient estimators, which complicates training and requires careful hyperparameter tuning. Sparse attention mechanisms are a deterministic alternative, but they lack a way to regularize the rationale extraction (e.g., to control the sparsity of a text highlight or the number of alignments). In this paper, we present a unified framework for deterministic extraction of str…
Compressed Sensor Caching and Collaborative Sparse Data Recovery with Anchor Alignment
Institute of Communications Engineering, National Tsing Hua University（国立清华大学通信工程研究所）；National Central University（国立中央大学）；National Yang Ming Chiao Tung University（国立阳明交通大学）
Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction
Swiss Data Science Center (SDSC) in Paul Scherrer Institute (PSI)（瑞士数据科学中心（SDSC）在保罗·舍勒研究所（PSI））；Swiss Data Science Center (SDSC) and ETH Zurich（瑞士数据科学中心（SDSC）和苏黎世联邦理工学院）；Swiss Data Science Center (SDSC) and Paul Scherrer Institute (PSI)（瑞士数据科学中心（SDSC）和保罗·舍勒研究所（PSI））
York University（约克大学）；University of Toronto（多伦多大学）；Kempner Institute, Harvard University（哈佛大学凯姆纳研究所）；Vector Institute（向量研究所）；Samsung AI Centre（三星人工智能中心）；Trajectory Labs（轨迹实验室）
SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）；Peng Cheng Laboratory（鹏城实验室）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Meituan, Beijing（美团，北京）；University of Chinese Academy of Sciences（中国科学院大学）；College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment
Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany（马克斯·普朗克研究所信息学院，萨尔兰信息学院，德国萨尔布吕肯）；Department of Language Science and Technology, Saarland University, Saarbrücken, Germany（语言科学与技术系，萨尔兰大学，德国萨尔布吕肯）
Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
Zhejiang University（浙江大学）；Nanyang Technological University（南洋理工大学）；The Hong Kong University of Science and Technology（香港科技大学）；Tsinghua University（清华大学）
CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
Southeast University（东南大学）；ByteDance Inc.（字节跳动公司）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其交叉应用重点实验室（东南大学），中华人民共和国教育部，中国）
