Search

Involving collaborative information in Large Language Models (LLMs) is a promising technique for adapting LLMs for recommendation. Existing methods achieve this by concatenating collaborative features with text tokens into a unified sequence input and then fine-tuning to align these features with LLM's input space. Although effective, in this work, we identify two limitations when adapting LLMs to recommendation tasks, which hinder the integration of general knowledge and collaborative information, resulting in sub-optimal recommendation performance. (1) Fine-tuning LLM with recommendation data can undermine its inherent world knowledge and fundamental competencies, which are crucial for interpreting and inferring recommendation text. (2) Incorporating collaborative features into textual prompts disrupts the semantics of the original prompts, preventing LLM from generating appropriate outputs. In this paper, we propose a new paradigm, CoRA (an acronym for Collaborative LoRA), with a collaborative weights generator. Rather than input space alignment, this method aligns collaborative information with LLM's parameter space, representing them as incremental weights to update LLM's output. This way, LLM perceives collaborative information without altering its general knowledge and text inference capabilities. Specifically, we employ a collaborative filtering model to extract user and item embeddings, converting them into collaborative weights with low-rank properties through the collaborative weights generator. We then merge the collaborative weights into LLM's weights, enabling LLM to perceive the collaborative signals and generate personalized recommendations without fine-tuning or extra collaborative tokens in prompts. Extensive experiments confirm that CoRA effectively integrates collaborative information into LLM, enhancing recommendation performance.

Graph Neural Networks (GNNs)-based recommendation algorithms typically assume that training and testing data are drawn from independent and identically distributed (IID) spaces. However, this assumption often fails in the presence of out-of-distribution (OOD) data, resulting in significant performance degradation. In this study, we construct a Structural Causal Model (SCM) to analyze interaction data, revealing that environmental confounders (e.g., the COVID-19 pandemic) lead to unstable correlations in GNN-based models, thus impairing their generalization to OOD data. To address this issue, we propose a novel approach, graph representation learning via causal diffusion (CausalDiffRec) for OOD recommendation. This method enhances the model's generalization on OOD data by eliminating environmental confounding factors and learning invariant graph representations. Specifically, we use backdoor adjustment and variational inference to infer the real environmental distribution, thereby eliminating the impact of environmental confounders. This inferred distribution is then used as prior knowledge to guide the representation learning in the reverse phase of the diffusion process to learn the invariant representation. In addition, we provide a theoretical derivation that proves optimizing the objective function of CausalDiffRec can encourage the model to learn environment-invariant graph representations, thereby achieving excellent generalization performance in recommendations under distribution shifts. Our extensive experiments validate the effectiveness of CausalDiffRec in improving the generalization of OOD data, and the average improvement is up to 10.69% on Food, 18.83% on KuaiRec, 22.41% on Yelp2018, and 11.65% on Douban datasets., Comment: 14 pages

Prompt tuning is a promising method to fine-tune a pre-trained language model without retraining its large-scale parameters. Instead, it attaches a soft prompt to the input text, whereby downstream tasks can be well adapted by merely learning the embeddings of prompt tokens. Nevertheless, existing methods still suffer from two challenges: (i) they are hard to balance accuracy and efficiency. A longer (shorter) soft prompt generally leads to a better(worse) accuracy but at the cost of more (less) training time. (ii)The performance may not be consistent when adapting to different downstream tasks. We attribute it to the same embedding space but responsible for different requirements of downstream tasks. To address these issues, we propose an Efficient Prompt Tuning method (EPT) by multi-space projection and prompt fusion. Specifically, it decomposes a given soft prompt into a shorter prompt and two low-rank matrices, significantly reducing the training time. Accuracy is also enhanced by leveraging low-rank matrices and the short prompt as additional knowledge sources to enrich the semantics of the original short prompt. In addition, we project the soft prompt into multiple subspaces to improve the performance consistency, and then adaptively learn the combination weights of different spaces through a gating network. Experiments on 13 natural language processing downstream tasks show that our method significantly and consistently outperforms 11 comparison methods with the relative percentage of improvements up to 12.9%, and training time decreased by 14%.

A dynamic temperature compensation method is presented to stabilize the wavelength of the entangled biphoton source, which is generated via the spontaneous parametric down-conversion based on a MgO: PPLN waveguide. Utilizing the dispersive Fourier transformation technique combined with a digital proportional-integral-differential algorithm, the small amount of wavelength variation can be instantly identified and then compensated with active temperature correction. The long-term wavelength stability, assessed though Allan deviation, shows nearly a hundredfold enhancement, reaching 2.00*10^(-7) at the averaging time of 10000 s. It offers a simple, ready-to-use solution for precise wavelength control in quantum information processing.

Recently, sign-aware graph recommendation has drawn much attention as it will learn users' negative preferences besides positive ones from both positive and negative interactions (i.e., links in a graph) with items. To accommodate the different semantics of negative and positive links, existing works utilize two independent encoders to model users' positive and negative preferences, respectively. However, these approaches cannot learn the negative preferences from high-order heterogeneous interactions between users and items formed by multiple links with different signs, resulting in inaccurate and incomplete negative user preferences. To cope with these intractable issues, we propose a novel \textbf{L}ight \textbf{S}igned \textbf{G}raph Convolution Network specifically for \textbf{Rec}ommendation (\textbf{LSGRec}), which adopts a unified modeling approach to simultaneously model high-order users' positive and negative preferences on a signed user-item interaction graph. Specifically, for the negative preferences within high-order heterogeneous interactions, first-order negative preferences are captured by the negative links, while high-order negative preferences are propagated along positive edges. Then, recommendation results are generated based on positive preferences and optimized with negative ones. Finally, we train representations of users and items through different auxiliary tasks. Extensive experiments on three real-world datasets demonstrate that our method outperforms existing baselines regarding performance and computational efficiency. Our code is available at \url{https://anonymous.4open.science/r/LSGRec-BB95}.

Sequential recommendation aims to provide users with personalized suggestions based on their historical interactions. When training sequential models, padding is a widely adopted technique for two main reasons: 1) The vast majority of models can only handle fixed-length sequences; 2) Batching-based training needs to ensure that the sequences in each batch have the same length. The special value \emph{0} is usually used as the padding content, which does not contain the actual information and is ignored in the model calculations. This common-sense padding strategy leads us to a problem that has never been explored before: \emph{Can we fully utilize this idle input space by padding other content to further improve model performance and training efficiency?} In this paper, we propose a simple yet effective padding method called \textbf{Rep}eated \textbf{Pad}ding (\textbf{RepPad}). Specifically, we use the original interaction sequences as the padding content and fill it to the padding positions during model training. This operation can be performed a finite number of times or repeated until the input sequences' length reaches the maximum limit. Our RepPad can be viewed as a sequence-level data augmentation strategy. Unlike most existing works, our method contains no trainable parameters or hyperparameters and is a plug-and-play data augmentation operation. Extensive experiments on various categories of sequential models and five real-world datasets demonstrate the effectiveness and efficiency of our approach. The average recommendation performance improvement is up to 60.3\% on GRU4Rec and 24.3\% on SASRec. We also provide in-depth analysis and explanation of what makes RepPad effective from multiple perspectives. Our datasets and codes are available at \url{https://github.com/KingGugu/RepPad}., Comment: Accepted by RecSys 2024

The Hubble constant, $H_0$, which is a crucial parameter in astrophysics and cosmology, is under significant tension. We explore an independent technique to measure $H_0$ based on the time-delay cosmography with strong gravitational lensing of a supernova lensed by a galaxy cluster, focusing on SN Refsdal in MACS J1149.5+2223, the first gravitationally lensed supernova with resolved multiple images. We carefully examine the dependence of constraints on the Hubble constant on the choice of lens mass models, employing 23 lens mass models with different assumptions on dark matter halos and external perturbations. Remarkably, we observe that the dependence on the choice of lens mass models is not significantly large, suggesting the robustness of the constraint on the Hubble constant from SN Refsdal. We combine measurements for the 23 lens mass models to obtain $H_0=70.0^{+4.7}_{-4.9}km/s/Mpc$ assuming equal weighting. We find that best-fitting Hubble constant values correlate with radial density profiles of the lensing cluster, implying a room for improving the constraint on the Hubble constant with future observations of more multiple images. We also find a clear correlation between best-fitting Hubble constant values and magnification factors of supernova multiple images. This correlation highlights the importance of gravitationally lensed Type Ia supernovae for accurate and robust Hubble constant measurements., Comment: 12 pages,7 figures, 2 tables. Comments are welcome!

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely overlooked. In this work, we reveal that the introduction of LLMs into recommendation models presents new security vulnerabilities due to their emphasis on the textual content of items. We demonstrate that attackers can significantly boost an item's exposure by merely altering its textual content during the testing phase, without requiring direct interference with the model's training process. Additionally, the attack is notably stealthy, as it does not affect the overall recommendation performance and the modifications to the text are subtle, making it difficult for users and platforms to detect. Our comprehensive experiments across four mainstream LLM-based recommendation models demonstrate the superior efficacy and stealthiness of our approach. Our work unveils a significant security gap in LLM-based recommendation systems and paves the way for future research on protecting these systems., Comment: ACL 2024 Main

The $Omh^2(z_i,z_j)$ two point diagnostics was proposed as a litmus test of $\Lambda$CDM model and measurements of cosmic expansion rate $H(z)$ have been extensively used to perform this test. The results obtained so far suggested a tension between observations and predictions of the $\Lambda$CDM model. However, the dataset of $H(z)$ direct measurements from cosmic chronometers and BAO was quite limited. This motivated us to study the performance of this test on a larger sample obtained in an alternative way. In this Letter, we propose that gravitational wave (GW) standard sirens could provide large samples of $H(z)$ measurements in the redshift range of $0

Multimodal recommendation aims to model user and item representations comprehensively with the involvement of multimedia content for effective recommendations. Existing research has shown that it is beneficial for recommendation performance to combine (user- and item-) ID embeddings with multimodal salient features, indicating the value of IDs. However, there is a lack of a thorough analysis of the ID embeddings in terms of feature semantics in the literature. In this paper, we revisit the value of ID embeddings for multimodal recommendation and conduct a thorough study regarding its semantics, which we recognize as subtle features of \emph{content} and \emph{structure}. Based on our findings, we propose a novel recommendation model by incorporating ID embeddings to enhance the salient features of both content and structure. Specifically, we put forward a hierarchical attention mechanism to incorporate ID embeddings in modality fusing, coupled with contrastive learning, to enhance content representations. Meanwhile, we propose a lightweight graph convolution network for each modality to amalgamate neighborhood and ID embeddings for improving structural representations. Finally, the content and structure representations are combined to form the ultimate item embedding for recommendation. Extensive experiments on three real-world datasets (Baby, Sports, and Clothing) demonstrate the superiority of our method over state-of-the-art multimodal recommendation methods and the effectiveness of fine-grained ID embeddings. Our code is available at https://anonymous.4open.science/r/IDSF-code/.

S. Kov\'acs proposed a conjecture on rigidity results induced by ample subsheaves of some exterior power of tangent bundles for projective manifolds. We verify the conjecture in the case of second exterior products under a rank condition. Besides, we prove a structure theorem satisfied by projective manifolds whose third exterior power of tangent bundle is nef. Additionally, we prove a weaker version of log Campana-Peternell conjecture for fourfolds. Finally, we give the structure of manifolds with a regular foliation whose exterior powers are strictly nef., Comment: correct some mistakes and add a section

Cross-modal retrieval has become popular in recent years, particularly with the rise of multimedia. Generally, the information from each modality exhibits distinct representations and semantic information, which makes feature tends to be in separate latent spaces encoded with dual-tower architecture and makes it difficult to establish semantic relationships between modalities, resulting in poor retrieval performance. To address this issue, we propose a novel framework for cross-modal retrieval which consists of a cross-modal mixer, a masked autoencoder for pre-training, and a cross-modal retriever for downstream tasks.In specific, we first adopt cross-modal mixer and mask modeling to fuse the original modality and eliminate redundancy. Then, an encoder-decoder architecture is applied to achieve a fuse-then-separate task in the pre-training phase.We feed masked fused representations into the encoder and reconstruct them with the decoder, ultimately separating the original data of two modalities. In downstream tasks, we use the pre-trained encoder to build the cross-modal retrieval method. Extensive experiments on 2 real-world datasets show that our approach outperforms previous state-of-the-art methods in video-audio matching tasks, improving retrieval accuracy by up to 2 times. Furthermore, we prove our model performance by transferring it to other downstream tasks as a universal model.

As a fundamental parameter for modern cosmology, the Hubble constant $H_0$ is experiencing a serious crisis. In this paper, we explore an independent approach to measure $H_0$ based on the time-delay cosmography with strong gravitational lensing of a quasar by a galaxy cluster. Specifically we focus on the strong lensing system SDSS J1004+4112 with the maximum image separation of 14.62$''$, the first system of a quasar lensed by a galaxy cluster with five multiple images. Incorporating the latest time-delay measurements, we investigate the lens model dependence from the combination of 16 different lens mass models. We find that the lens model dependence is indeed large, with the combined measurement of the Hubble constant of $H_0=67.5^{+14.5}_{-8.9}km/s/Mpc$ that is obtained by summing posteriors of the Hubble constant from the 16 models with equal weighting. Interestingly, our results show that the value of Hubble constant decreases as the complexity of the perturbation around the lens increases, although weighting based on positional errors of quasar images does not significantly improve the $H_0$ constraint. We find that the 16 different mass models predict largely different shapes of the lensed quasar host galaxy as well as other lensed galaxies behind the cluster. By selecting two mass models that best reproduces those shapes, the constraint on the Hubble constant is significantly tightened to $H_0=59.1^{+3.6}_{-3.5}km/s/Mpc$. While we caution that our analysis still does not fully explore all the possible mass model uncertainty, our results highlight the importance of including as many constraints as possible such as extended shapes of lensed galaxies for obtaining tight constraints on the Hubble constant from cluster-lensed quasar lens systems., Comment: 12 pages, 5 figures, 3 tables. Accepted for publication in PRD

Adversarial examples bring a considerable security threat to support vector machines (SVMs), especially those used in safety-critical applications. Thus, robustness verification is an essential issue for SVMs, which can provide provable robustness against various kinds of adversary attacks. The evaluation results obtained through the robustness verification can provide a safe guarantee for the use of SVMs. The existing verification method does not often perform well in verifying SVMs with nonlinear kernels. To this end, we propose a method to improve the verification performance for SVMs with nonlinear kernels. We first formalize the adversarial robustness evaluation of SVMs as an optimization problem. Then a lower bound of the original problem is obtained by solving the Lagrangian dual problem of the original problem. Finally, the adversarial robustness of SVMs is evaluated concerning the lower bound. We evaluate the adversarial robustness of SVMs with linear and nonlinear kernels on the MNIST and Fashion-MNIST datasets. The experimental results show that the percentage of provable robustness obtained by our method on the test set is better than that of the state-of-the-art.

As a new approach to realizing high-precision time synchronization between remote time scales, quantum two-way time transfer via laboratory fiber link has shown significant enhancement of the transfer stability to several tens of femtoseconds. To verify its great potential in practical systems, the field test in long-haul installed fiber optic infrastructure is required to be demonstrated. In this paper, we implement the two-way quantum time transfer over a 103 km urban fiber link. A time transfer stability of 3.67 ps at 10 s and 0.28 ps at 40000 s has been achieved, despite the large attenuation of 38 dB leading to fewer than 40 correlated events per second. This achievement marks the first successful step of quantum two-way time transfer in the task of high-precision long-distance field transfer systems.