sentence-transformers How to use yjoonjang/reviewsearch-dense with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("yjoonjang/reviewsearch-dense")
sentences = [
"multi-modal imputation computational cost",
"title: Learning Flexible Forward Trajectories for Masked Molecular Diffusion\n\nsummary: This paper focuses on the adaptation problem of Masked Diffusion Models (MDMs) for discrete data in molecular graph generation. It points out that \"fixed, element-independent\" forward masking scheduling leads to different molecules collapsing to the same intermediate state in the forward trajectory, making reverse denoising, typically unimodal and predicting independently by node or edge, difficult to learn the correct reconstruction target. To address this, the paper proposes MELD: which learns the forward masking rate at the element level (node/edge) and assigns an independent erosion trajectory to each graph element through a parameterized noise scheduling network; it is jointly optimized with the reverse denoising network during training. The authors claim that MELD achieves high efficiency in unconditional generation of QM9 and ZINC250K graphs and outperforms standard MDM and several diffusion baselines in distribution alignment and property alignment.\n\nweaknesses and questions: 1.The element-level kernel renders the forward process non-equivariant, meaning the intermediate state distribution is affected by vertex permutations. For molecular graphs, this contradicts the fundamental principle that isomorphism should not alter the generative distribution. Current methods merely introduce a learnable embedding H for each graph element and \"randomly permutate columns\" to \"distinguish graph states with the same number of nodes/edges,\" but this does not restore the guarantee of permutation equivariance. It needs to be proven that this forward process, which breaks equivariance, does not induce dependencies on node labels and generalization issues, especially whether relabeling input nodes during testing maintains a consistent sampling distribution.\n\n2.The abstract and main text claim that MELD is \"the first diffusion model to achieve 100% chemigenicity in unconditional generation on QM9 and ZINC250K,\" but several MDM baselines in Table 1 also show 100%. The wording needs to be corrected.\n\n3.The paper does not provide an explicit collision risk function or upper and lower bound analysis; the loss in Equation (3) does not directly minimize the \"collision probability\". It is suggested to provide a computable proxy metric and its relationship with the gradient direction, or to supplement the appendix with a simplified derivation of the \"collision probability as a function of {𝑤_{𝑖}}\".\n\n4.The manuscript states that \"unless otherwise specified, standard MDM and MELD use the same DiT backbone,\" but were the other discrete/continuous diffusion baselines in Table 1 also retrained and had their backbones and training budgets aligned? If comparisons are only made within the MDM family without aligning the backbones/hyperparameters of external distributed models, the conclusions may overestimate the advantages of MELD. Please provide the number of training epochs, GPU configuration, total duration, and FLOPs in the appendix, as well as the retraining/reproduction practices for each baseline.\n\n5.The use of V.U.N.↑ in Tables 3 and 6 lacks a clear explanation of its meaning and calculation in the text (it seems to be a composite score for Validity/Uniqueness/Novelty?). Please define it explicitly at its first appearance in the text.\n1.The statement \"first 100% validity\" conflicts with Table 1. It is recommended to change it to \"significantly reduced FCD/NSPDK while maintaining 100% validity.\" Could you please report the confidence intervals for inefficiency (multiple sampling)?\n\n2.Can a more systematic comparison be made between the key differences and complexity of existing \"adaptive/category-level\" scheduling (such as DiffusionBERT, GenMD4, TabDiff) and the \"element-level\" scheduling in this paper? Currently, only a rough comparison is made in Table 3, lacking a theoretical analysis of the differences in expressive power.\n\n3.Please list the number of training epochs, learning rate, scheduler, backbone, number of GPUs, and training time for all baselines; and specify which baselines were retrained by the authors and which were reproduced from the original paper.\n\n4.Please add \"Node relabeling robustness test\" (variance of distribution index/property MAE under multiple labels of the same molecule).\n\n5.Table 5 only performs isomorphism counting on 12 nodes/131 samples, which is costly but has a small sample size; it is recommended to provide estimation methods for larger scales (such as approximate GI or fingerprint hash upper/lower bounds) and statistical confidence intervals.",
"title: ICFI: A Feature Importance Measure For Multi-Class Classification\n\nsummary: The paper proposes a novel feature importance method for multi-class classification. The method tackles the problem of providing not only one set of feature importances, but one for each pair of classes, thus offering more insight into the classifier. The method is based on the idea of observing decrease in empirical risk when two classes are combined, in combination with permutation-based feature importance. Some experiments are provided showing that the method gives sensible results and outperforms GSHAP adapted to the same problem.\n\nweaknesses and questions: The proposed method is relatively simple and does not bring any extremely innovative methodology or theoretical results, which is nothing wrong by itself, but the I would expect a very strong empirical evaluation or (even better) a practical use-case that demonstrates not only that the method works but that the problem of requiring additional insights into (pairwise) relationships between classes is really a problem in need of a solution.\n\nThe current experiments do not convince me (see Questions). As the authors also say, evaluation of XAI is a big challenge and there doesn't seem to be any shortcut to a sound empirical evaluation (https://icml.cc/virtual/2025/poster/40169). The first two experiments establish that there is nothing clearly wrong with the method, which is OK. The retraining experiment and comparison with GSHAP I do not understand. If the goal of the method is to provide insights into how the model classifies, then this is far from a realistic assessment (yes, it is common to do this in XAI/ML papers, but it doesn't make it any less unrealistic). Also, it seems to me that GSHAP was forced into this comparison, not being a method developed for the same purpose. I might be wrong, but the paper doesn't do a good job of describing exactly what GSHAP is or how it was adapted.\n\nAnd I might have other issues with the paper on things that I currently don't quite understand and/or were not explained clearly enough (also see Questions).\n\nMinor comments:\n- Some extra effort seems to have gone into squeezing this to fit the page limit (Figure 6 caption has no space to breathe, etc.).\n- ).One\n- The proposed method operates on model risk not on model predictions directly. So, technically, it is not explaining what the model does, but what features contribute to the models predictive performance. Often the same, but not always.\nQ1: Finally, why not include some global feature importance into the comparison? The problem of masking the feature importance of globally less important features that are important for certain pairs of classes might be exaggerated. I'd imagine that for a low number of classes the global ordering would be decent (definitely better than random). \n\nQ2. Computational complexity: First, it would really help if the computational complexity is stated more explicitly, instead of \"in line with existing permutation methods but cheaper than SHAP\". Second, I'm not convinced that the latter is correct. The proposed method requires for each feature a constant number of permutations and each permutation requires a model prediction? Any decent implementation of SHAP should also be linear in the number of features and will contain the model prediction (you don't go through all subsets of coalitions).\n\nQ3. Permutation importance has certain failure cases, compared to SHAP, for example. Why not combine the idea of combining two classes but then use Shapley values instead of permutation importance? \n\nQ4. I'd remove the explicit \"Definition 1\" from definition of the pairwise feature importance problem. It is not necessary and it is not precise. Informally we would probably agree on what \"as it pertains to separating the target classes $\\sigma$ and $\\rho$\" means, but what does it really mean? A model never trully 100% focuses on separating only two classes (unless there are only two classes).\n\nQ5. The interval computation in A.3 seems like overkill. The (Bayesian posterior) mean and standard deviation of a process where 100 independent samples are given is estimated using Markov Chain Monte Carlo? Unless I'm missing something, the only possible justification would be that we use uniform priors on the two parameters and therefore can't use the analytical solution. But if we are going to be so precise as to not allow values outside of [0,1] then why use a Gaussian likelihood, which is clearly not appropriate. Burn-in also doesn't make sense (why not just pick a sensible starting value, like the empirical mean and standard deviation). To summarize, average +/- 1.96 * standard deviation of the sample / sqrt(100) should give essentially the same results.\n\nQ6. I'm unsure about the upper/lower bound requirement. First, the requirements, as stated, would allow for a method that assigns arbitrarily low negative feature importances (we require irrelevant features to have 0 and to have an upper bound; there is nothing saying that a relevant feature can't have a negative importance, for example, if it decreases predictive performance). I'll assume that the intention was for them to be bounded between 0 and an upper bound (which might as well be 1). I'm not convinced by the argument that people prefer bounded things therefore bounding is better. That is, it is mathematically easy to bound things, but with it we change the scale of the feature importance. Are these importances even comparable across class pairs for same risk? Are they comparable across different risks?",
"title: Learning Optimal Multimodal Information Bottleneck Representations\n\nsummary: The author introduces a theoretically guaranteed multimodal information bottleneck approach. This method dynamically adjusts the regularization weights of each modality by considering the varying degrees of task-relevant information across different modalities. Theoretically, the optimization objective proposed by the author is of a remarkably straightforward form, and the practical loss function serves as an upper bound to this theoretical objective, thereby ensuring the feasibility.\n\n\n#### update after rebuttal: I don't change my assessment.\n\nweaknesses and questions: The article is logically structured, with clearly defined and reader-friendly symbols. The theoretical section is particularly detailed and rigorous.\nIn the experiments, the non-MIB-based methods only include some basic approaches. I am curious about how they compare with newer methods:\nPeng, Xiaokang, et al. \"Balanced multimodal learning via on-the-fly gradient modulation.\" Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022.\n\nZhang, Xiaohui, et al. \"Multimodal representation learning by alternating unimodal adaptation.\" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.\n\nI harbor a degree of skepticism towards the reasoning in Equation (3), which posits that concatenating $e_i$ enhances the model's learning by improving the signal-to-noise ratio. Typically, the introduction of signal-to-noise ratio considerations involves additive noise, such as ( z_i^{noise} = z_i + e_i ), rather than direct concatenation. Moreover, the ablation studies do not include relevant content to substantiate this.",
"title: A Structured Pruning Algorithm for Model-based Deep Learning\n\nsummary: This paper proposes a structured pruning method for model-based deep learning in inverse problems. The proposed method, SPADE, reduces the computational complexity of model-based networks at test-time by pruning its non-essential weights. In addition, three different fine-tuning methods are introduced for the pruned networks to reduce performance loss. SPADE is evaluated on compressed sensing MRI and image super-resolution, and is shown to speed up inference with minimal performance degradation.\n\nweaknesses and questions: Weaknesses:\n- The contributions of the paper are mostly comprised of a combination of existing techniques such as the pruning algorithm and the fine-tuning techniques.\n- The method is not compared with other methods for improving inference speed, such as [1] or [2] mentioned in the paper. The lack of this comparison makes it difficult to quantify the significance of the results. As an example, there is a 0.77 dB PSNR drop with a 51% speed up at test-time (Table 1) for compressed sensing MRI which seems to be a large performance reduction, and it is unclear how this compares to existing methods.\n\n[1] J. Liu, Y. Sun, W. Gan, X. Xu, B. Wohlberg, and U. S. Kamilov. SGD-Net: Efficient Model-Based\nDeep Learning With Theoretical Guarantees. IEEE Trans. Computational Imag., 7:598–610,\n2021.\n\n[2] J. Tang and M. Davies. A fast stochastic plug-and-play ADMM for imaging inverse problems. arXiv\npreprint arXiv:2006.11630, 2020.\n- How much does the training time increase for SPADE, compared with the baseline unpruned model-based network?\n- Is it possible to combine fine-tuning losses, rather than view them as independent techniques, and could that help preserve performance?\n- How does the memory complexity change at test-time? Memory complexity is also a quite important consideration for which discussion has not been included.\n\nSuggestions:\n\n- The introduction, and the \"DL and MBDL.\" subsection in the background are repetitive. For instance, the equation for PnP/RED does not seem to contribute to the story of the paper. The background can be shortened to include more experiments in the main paper, such as the visual results (Figure 6-8) in the supplemental, which are crucial for compressed sensing MRI. \n- Typographical errors should be fixed via proofreading.",
"title: FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion\n\nsummary: This paper proposes an MOE-based model to handle multimodal data fusion. It addresses two challenges: missing modalities and irregularly sampled data trajectories. A Laplace gating function is applied to the MoE Backbone. An entropy regularization loss is proposed to ensure balanced and stable expert utilization. The author validates the method in diverse datasets.\n\nweaknesses and questions: Addressing the following weaknesses may improve the paper: \n\n1. The author should clearly distinguish the proposed method and others’ modules. From the paper, the Laplace gating function is proposed as a new one. I am not sure the author made some contributions to the encoder design, router design, and loss design. The author should make more illustrations about the contributions, not just combine other people’s work together. \n\n2. The experimental results are not extensive. The author should clearly demonstrate the data modality of the chosen benchmarks. It seems that other modalities, such as text, are not included. The author should explain this. \n\n3. Please explain more concisely how the gating functions can stabilize the imbalance and sparse multi-modal data. The paper should point this out more concisely and better with experimental results. Too many mathematical proofs and theorems in Sec.3 seem not helpful in illustrating the advantages of the proposed method.\nPlease see the weakness part to answer the questions.",
"title: Compute Where It Counts: Adaptive Compute Allocation for Large Language Models via Learned Granular Sparsity\n\nsummary: CWIC (Compute Where it Counts) introduces a novel method for training sparse LLMs by making sparsity thresholds learnable parameters. The key contributions are: (1) learned contextual thresholds that are optimized using STEs, allowing models to dynamically allocate different amounts of compute to different tokens and weight matrices, and (2) granular sparsity that partitions matrix columns into smaller \"stripes\" for more expressive sparsity patterns.\n\nweaknesses and questions: Major Concerns\n\n1) I am not sure about the claim - *STE improves performance by removing the variance imparted on the grads when the values of G fluctuate...*: Using STE seems overly aggressive for the use-case? I think there needs to be more justification around this choice. Supporting experiments to compare that this is as a winning choice might also be helpful. Right now, this seems to more like a empirical tuning based selection?\n- If this choice is derived from JumpReLU - their gradient estimator worked for SAE reconstruction doesn't automatically validate these additional modifications for multi-layer distillation. Current explanation is not sufficient for a convincing argument.\n\nIn general, I think section 3.3 is poorly written. Authors should re-word their ideas more clearly here. \n\n2) No analysis of why related kernel choice is better than alternatives?\n\n3) The psuedo-derivative bandwidth (lines 220-224): The interaction between adaptive bandwidth $(\\epsilon_i = \\alpha\\epsilon · std(x_i))$ and input whitening (Section 3.4) is unclear - is std computed on whitened or raw values? How does this affect gradient scales?\n- No comparison of adaptive vs. fixed bandwidth for pseudo-derivatives.\n\n4) Experimental concern: The distillation data includes benchmark training sets (MMLU, ARC, WinoGrande) repeated 5×, which may inflate evaluation scores (refer: appendix C I believe). I think reporting scores on benchmarks not in training data would be a stronger claim.\n\n5) Loss function: Authors need to explain how to interpret this. Right now, it looks asymmetrical: the loss only penalizes using too many parameters, not too few? In other words, it will keep on minimizing, i.e nothing stops the model from becoming 10× sparse if that happens to minimize distillation loss? It seems one would need careful tuning/warm starting to counter this or is there a implicit effect from distillation loss (or am I understanding this wrong)?\n\nI strongly think the presentation wrt to the key ideas (section 3.2-3.6) need to be improved to make the author's work more accessible and make a convincing argument towards a lot of different empirical choices. Additionally, I found the concatenation operator to be a bit confusing (line 180-181), maybe there is a better way to mathematically denote it?\nNA",
"title: Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling\n\nsummary: This paper focuses on the task of phenotype imputation and proposes utilizing multi-modal data to gain insights that facilitate the evaluation of patients' overall health status. Specifically, the authors design a framework based on view decoupling, which involves segregating the modeling of biological data and phenotype data to avoid the impact of data heterogeneity and view conflict. To alleviate the influence of noise and irrelevant information in the biological data, a novel contrastive knowledge distillation method is proposed. Furthermore, the authors conduct extensive experiments to demonstrate the superiority of the proposed model.\n\nweaknesses and questions: 1.\tThe model includes multiple components. It would be beneficial to discuss the time complexity of the proposed method. Specifically, an analysis of the computational efficiency for each component, as well as the overall model, would provide valuable insights.\n2.\tThe patients in the experiments are selected from those with Alzheimer's disease and related dementias. It would be helpful to explain the rationale behind selecting this particular patient set. Additionally, it is important to discuss whether the model is applicable to other cohorts.\n3.\tWhy can't recent models, such as M3Care, Graph, and MUSE, directly address the need for integrating biological data and EHR data?\n4.\tThe proposed method involves multiple loss functions. Adding these losses to Figure 1 would aid understanding. Including pseudocode for the algorithm would also be helpful.\nPlease refer to weaknesses.",
"title: Distributed Parallel Gradient Stacking(DPGS): Solving Whole Slide Image Stacking Challenge in Multi-Instance Learning\n\nsummary: This paper introduces Distributed Parallel Gradient Stacking (DPGS), a framework designed to address the challenge of non-stackable data in Multiple Instance Learning (MIL) for Whole Slide Image (WSI) analysis. The authors propose two key components: (1) DPGS, which enables parallel processing of variable-length MIL bags by distributing them across multiple GPUs and aggregating their gradients, and (2) Deep Model-Gradient Compression (DMGC), which reduces communication overhead during distributed training through joint compression of gradients and model parameters. Experiments on Camelyon16 and TCGA-Lung datasets demonstrate significant improvements in both training speed (up to 31× faster) and classification accuracy (up to 9.3% increase) compared to baseline methods.\n\nweaknesses and questions: Strengths:\n1.\tThe mathematical derivations showing equivalence to mini-batch training are sound.\n2.\tThe gradient compression approach (DMGC) offers an interesting extension to existing gradient compression techniques.\n3.\tThe ablation studies provide useful insights into the factors affecting performance within their framework.\nWeaknesses:\n1.\tHigh resource requirements: Although the speed-up performance is impressive, the method requires multiple GPUs and high-bandwidth connections, significantly limiting its practical applicability in many research and clinical settings.\n2.\tMissing comparisons to simpler alternatives: The paper doesn't evaluate simple alternatives such as uniform sampling that could potentially achieve similar results with much less complexity.\n3.\tOutdated baselines: The paper relies on comparisons with older MIL methods rather than current state-of-the-art approaches.\n4.\tUnclear feature extraction: The \"multi-scale\" features referenced throughout the paper are not adequately defined.\n5.\tLimited relevance given foundation models: The paper doesn't acknowledge or compare against foundation models that have demonstrated near-perfect performance on the same datasets.\n1.\tCould you provide a clear definition of the \"multi-scale\" feature extraction process used in your experiments, including architectures and implementation details?\n2.\tHave you compared your approach with simpler methods like uniform sampling from each WSI to create fixed-length bags that could be trained with standard batch processing?\n3.\tCould you explain your experimental setting and the reason why you did not consider current foundation model-based approaches (UNI [1], CONCH [2], PLIP [3], etc.) that have demonstrated state-of-the-art performance on the same datasets?\n4.\tWhat is the minimum hardware configuration required to achieve meaningful benefits from your approach compared to single-GPU training?\n5.\tWhy did you choose to compare against older MIL methods rather than more recent approaches that might represent stronger baselines?\nI will consider raising the overall recommendation score if these questions are solved in the rebuttal phase.\n[1] Chen, Richard J., et al. \"Towards a general-purpose foundation model for computational pathology.\" Nature Medicine 30.3 (2024): 850-862.\n[2] Lu, Ming Y., et al. \"A visual-language foundation model for computational pathology.\" Nature Medicine 30.3 (2024): 863-874.\n[3] Huang, Zhi, et al. \"A visual–language foundation model for pathology image analysis using medical twitter.\" Nature medicine 29.9 (2023): 2307-2316."
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [9, 9] 
