Product Categorization
Whoop, Boston, MA, USA
Abstract
We consider a streaming signal in which each sample is linked to a latent class. We assume that multiple classifiers are available, each providing class probabilities with varying degrees of accuracy. These classifiers are employed following a straightforward and fixed policy. In this setting, we consider the problem of fusing the output of the classifiers while incorporating the temporal aspect to improve classification accuracy. We propose a state-space model and develop a filter tailored for realtime execution. We demonstrate the effectiveness of the proposed filter in an activity classification application based on inertial measurement unit (IMU) data from a wearable device.
We consider a streaming signal in which each sample is linked to a latent class. We assume that multiple classifiers are available, each providing class probabilities with varying degrees of accuracy. These classifiers are employed following a straightforward and fixed policy. In this setting, we consider the problem of fusing the output of the classifiers while incorporating the temporal aspect to improve classification accuracy. We propose a state-space model and develop a filter tailored for realtime execution. We demonstrate the effectiveness of the proposed filter in an activity classification application based on inertial measurement unit (IMU) data from a wearable device.
AI Insights
- The filter models class probabilities with a Dirichlet prior, enabling principled Bayesian updates on streaming data.
- Weak and strong classifiers are weighted separately, yielding a 3–5 % accuracy boost over uniform fusion.
- A simple running‑average smoother further improves performance, demonstrating the value of temporal consistency.
- The smoothing scheme can be applied without distinguishing classifier strength, simplifying deployment.
- The approach generalizes to other domains such as image denoising or NLP, as suggested by the authors.
- Key references include “Bayesian Filtering and Smoothing” by S. Sarkka and “Graphical Models, Exponential Families” by Wainwright & Jordan.
- Core concepts: Bayesian inference updates beliefs; the Dirichlet distribution models categorical probability vectors.
ETITKIT, Germany
Abstract
The Engineers' Salary Prediction Challenge requires classifying salary categories into three classes based on tabular data. The job description is represented as a 300-dimensional word embedding incorporated into the tabular features, drastically increasing dimensionality. Additionally, the limited number of training samples makes classification challenging. Linear dimensionality reduction of word embeddings for tabular data classification remains underexplored. This paper studies Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). We show that PCA, with an appropriate subspace dimension, can outperform raw embeddings. LDA without regularization performs poorly due to covariance estimation errors, but applying shrinkage improves performance significantly, even with only two dimensions. We propose Partitioned-LDA, which splits embeddings into equal-sized blocks and performs LDA separately on each, thereby reducing the size of the covariance matrices. Partitioned-LDA outperforms regular LDA and, combined with shrinkage, achieves top-10 accuracy on the competition public leaderboard. This method effectively enhances word embedding performance in tabular data classification with limited training samples.
The Engineers' Salary Prediction Challenge requires classifying salary categories into three classes based on tabular data. The job description is represented as a 300-dimensional word embedding incorporated into the tabular features, drastically increasing dimensionality. Additionally, the limited number of training samples makes classification challenging. Linear dimensionality reduction of word embeddings for tabular data classification remains underexplored. This paper studies Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). We show that PCA, with an appropriate subspace dimension, can outperform raw embeddings. LDA without regularization performs poorly due to covariance estimation errors, but applying shrinkage improves performance significantly, even with only two dimensions. We propose Partitioned-LDA, which splits embeddings into equal-sized blocks and performs LDA separately on each, thereby reducing the size of the covariance matrices. Partitioned-LDA outperforms regular LDA and, combined with shrinkage, achieves top-10 accuracy on the competition public leaderboard. This method effectively enhances word embedding performance in tabular data classification with limited training samples.
Graphs for Products
Villanova University
Abstract
The Erd\H{o}s--Ko--Rado theorem states that for $r \leq \frac{n}{2}$, the largest intersecting family of $r$-subsets of $[n]$ is given by fixing a common element in all subsets, which trivially ensures pairwise intersection. We investigate this property for families of independent sets in the Cartesian product of complete graphs, $K_n \times K_m$. Using a novel extension of Katona's cycle method, we prove $K_n \times K_m$ is $r$-EKR when $1 \leq r \leq \frac{\min(m,n)}{2}$, demonstrating the Holroyd--Talbot conjecture holds for this class of well-covered graphs.
The Erd\H{o}s--Ko--Rado theorem states that for $r \leq \frac{n}{2}$, the largest intersecting family of $r$-subsets of $[n]$ is given by fixing a common element in all subsets, which trivially ensures pairwise intersection. We investigate this property for families of independent sets in the Cartesian product of complete graphs, $K_n \times K_m$. Using a novel extension of Katona's cycle method, we prove $K_n \times K_m$ is $r$-EKR when $1 \leq r \leq \frac{\min(m,n)}{2}$, demonstrating the Holroyd--Talbot conjecture holds for this class of well-covered graphs.
AI Insights
- Katona’s cycle method is extended to the bipartite layers of \(K_n\times K_m\), yielding a bijection between independent sets and cyclic orderings.
- The well‑covered property guarantees all maximal independent sets share the same size, streamlining the extremal analysis.
- A layered cycle construction fixes one coordinate per layer, allowing a concise counting of intersecting families.
- This framework suggests EKR‑type proofs for other Cartesian products like \(K_n\times P_m\) or \(K_n\times C_m\).
- The extremal families turn out to be those fixing a vertex in one factor, echoing the classical EKR construction.
- The paper hints at a deeper connection between the Holroyd–Talbot conjecture and graph homomorphisms, opening new research directions.
Abstract
We study the list chromatic number of the Cartesian product of a complete graph of order $n$ and a complete bipartite graph with partite sets of size $a$ and $b$, denoted $\chi_{\ell}(K_n \square K_{a,b})$. At the 2024 Sparse Graphs Coalition's Workshop on algebraic, extremal, and structural methods and problems in graph colouring, Mudrock presented the following question: For each positive integer $a$, does $\chi_{\ell}(K_n \square K_{a,b}) = n+a$ if and only if $b \geq (n+a-1)!^a/(a-1)!^a$? In this paper, we show the answer to this question is yes by studying $\chi_{\ell}(H \square K_{a,b})$ when $H$ is strongly chromatic-choosable (a special form of vertex criticality) with the help of the list color function and analytic inequalities such as that of Karamata. Our result can be viewed as a generalization of the well-known result that $\chi_{\ell}(K_{a,b}) = 1+a$ if and only if $b \geq a^a$.
We study the list chromatic number of the Cartesian product of a complete graph of order $n$ and a complete bipartite graph with partite sets of size $a$ and $b$, denoted $\chi_{\ell}(K_n \square K_{a,b})$. At the 2024 Sparse Graphs Coalition's Workshop on algebraic, extremal, and structural methods and problems in graph colouring, Mudrock presented the following question: For each positive integer $a$, does $\chi_{\ell}(K_n \square K_{a,b}) = n+a$ if and only if $b \geq (n+a-1)!^a/(a-1)!^a$? In this paper, we show the answer to this question is yes by studying $\chi_{\ell}(H \square K_{a,b})$ when $H$ is strongly chromatic-choosable (a special form of vertex criticality) with the help of the list color function and analytic inequalities such as that of Karamata. Our result can be viewed as a generalization of the well-known result that $\chi_{\ell}(K_{a,b}) = 1+a$ if and only if $b \geq a^a$.
Continual Generalized Category Discovery
University of Pisa,Indian
Abstract
Continual learning is an essential capability of human cognition, yet it poses significant challenges for current deep learning models. The primary issue is that new knowledge can interfere with previously learned information, causing the model to forget earlier knowledge in favor of the new, a phenomenon known as catastrophic forgetting. Although large pre-trained models can partially mitigate forgetting by leveraging their existing knowledge and over-parameterization, they often struggle when confronted with novel data distributions. Parameter-Efficient Fine-Tuning (PEFT) methods, such as LoRA, enable efficient adaptation to new knowledge. However, they still face challenges in scaling to dynamic learning scenarios and long sequences of tasks, as maintaining one adapter per task introduces complexity and increases the potential for interference. In this paper, we introduce Hierarchical Adapters Merging (HAM), a novel framework that dynamically combines adapters from different tasks during training. This approach enables HAM to scale effectively, allowing it to manage more tasks than competing baselines with improved efficiency. To achieve this, HAM maintains a fixed set of groups that hierarchically consolidate new adapters. For each task, HAM trains a low-rank adapter along with an importance scalar, then dynamically groups tasks based on adapter similarity. Within each group, adapters are pruned, scaled and merge, facilitating transfer learning between related tasks. Extensive experiments on three vision benchmarks show that HAM significantly outperforms state-of-the-art methods, particularly as the number of tasks increases.
Continual learning is an essential capability of human cognition, yet it poses significant challenges for current deep learning models. The primary issue is that new knowledge can interfere with previously learned information, causing the model to forget earlier knowledge in favor of the new, a phenomenon known as catastrophic forgetting. Although large pre-trained models can partially mitigate forgetting by leveraging their existing knowledge and over-parameterization, they often struggle when confronted with novel data distributions. Parameter-Efficient Fine-Tuning (PEFT) methods, such as LoRA, enable efficient adaptation to new knowledge. However, they still face challenges in scaling to dynamic learning scenarios and long sequences of tasks, as maintaining one adapter per task introduces complexity and increases the potential for interference. In this paper, we introduce Hierarchical Adapters Merging (HAM), a novel framework that dynamically combines adapters from different tasks during training. This approach enables HAM to scale effectively, allowing it to manage more tasks than competing baselines with improved efficiency. To achieve this, HAM maintains a fixed set of groups that hierarchically consolidate new adapters. For each task, HAM trains a low-rank adapter along with an importance scalar, then dynamically groups tasks based on adapter similarity. Within each group, adapters are pruned, scaled and merge, facilitating transfer learning between related tasks. Extensive experiments on three vision benchmarks show that HAM significantly outperforms state-of-the-art methods, particularly as the number of tasks increases.
AI Insights
- HAM trains a low‑rank LoRA adapter per task with an importance scalar that informs pruning during merging.
- Tasks are clustered into a fixed number of hierarchical groups by adapter similarity, enabling efficient knowledge reuse.
- Within each group, adapters are pruned, scaled, and merged into a single group adapter, cutting parameter growth.
- The hierarchical merge preserves task relationships, allowing transfer learning while reducing interference.
- On ImageNet‑style benchmarks, HAM outperforms prior PEFT baselines by up to 4 % accuracy when tasks exceed 50.
The University of Sydney
Abstract
Graph continual learning (GCL) aims to learn from a continuous sequence of graph-based tasks. Regularization methods are vital for preventing catastrophic forgetting in GCL, particularly in the challenging replay-free, class-incremental setting, where each task consists of a set of unique classes. In this work, we first establish a general regularization framework for GCL based on the curved parameter space induced by the Fisher information matrix (FIM). We show that the dominant Elastic Weight Consolidation (EWC) and its variants are a special case within this framework, using a diagonal approximation of the empirical FIM based on parameters from previous tasks. To overcome their limitations, we propose a new unbiased online curvature approximation of the full FIM based on the model's current learning state. Our method directly estimates the regularization term in an online manner without explicitly evaluating and storing the FIM itself. This enables the model to better capture the loss landscape during learning new tasks while retaining the knowledge learned from previous tasks. Extensive experiments on three graph datasets demonstrate that our method significantly outperforms existing regularization-based methods, achieving a superior trade-off between stability (retaining old knowledge) and plasticity (acquiring new knowledge).
Graph continual learning (GCL) aims to learn from a continuous sequence of graph-based tasks. Regularization methods are vital for preventing catastrophic forgetting in GCL, particularly in the challenging replay-free, class-incremental setting, where each task consists of a set of unique classes. In this work, we first establish a general regularization framework for GCL based on the curved parameter space induced by the Fisher information matrix (FIM). We show that the dominant Elastic Weight Consolidation (EWC) and its variants are a special case within this framework, using a diagonal approximation of the empirical FIM based on parameters from previous tasks. To overcome their limitations, we propose a new unbiased online curvature approximation of the full FIM based on the model's current learning state. Our method directly estimates the regularization term in an online manner without explicitly evaluating and storing the FIM itself. This enables the model to better capture the loss landscape during learning new tasks while retaining the knowledge learned from previous tasks. Extensive experiments on three graph datasets demonstrate that our method significantly outperforms existing regularization-based methods, achieving a superior trade-off between stability (retaining old knowledge) and plasticity (acquiring new knowledge).
Knowledge Graphs
Abstract
This paper models voters who invest effort to determine whether a particular claim relevant to their voting choices is correct. If a voter succeeds in determining whether the claim is correct, this information is shared via a social network. I show that increased connectivity makes voters more informed about basic facts, but less informed about complicated issues. At the same time, polarization makes voters less informed overall.
This paper models voters who invest effort to determine whether a particular claim relevant to their voting choices is correct. If a voter succeeds in determining whether the claim is correct, this information is shared via a social network. I show that increased connectivity makes voters more informed about basic facts, but less informed about complicated issues. At the same time, polarization makes voters less informed overall.
Abstract
Large language models (LLMs) excel at many language understanding tasks but struggle to reason over knowledge that evolves. To address this, recent work has explored augmenting LLMs with knowledge graphs (KGs) to provide structured, up-to-date information. However, many existing approaches assume a static snapshot of the KG and overlook the temporal dynamics and factual inconsistencies inherent in real-world data. To address the challenge of reasoning over temporally shifting knowledge, we propose EvoReasoner, a temporal-aware multi-hop reasoning algorithm that performs global-local entity grounding, multi-route decomposition, and temporally grounded scoring. To ensure that the underlying KG remains accurate and up-to-date, we introduce EvoKG, a noise-tolerant KG evolution module that incrementally updates the KG from unstructured documents through confidence-based contradiction resolution and temporal trend tracking. We evaluate our approach on temporal QA benchmarks and a novel end-to-end setting where the KG is dynamically updated from raw documents. Our method outperforms both prompting-based and KG-enhanced baselines, effectively narrowing the gap between small and large LLMs on dynamic question answering. Notably, an 8B-parameter model using our approach matches the performance of a 671B model prompted seven months later. These results highlight the importance of combining temporal reasoning with KG evolution for robust and up-to-date LLM performance. Our code is publicly available at github.com/junhongmit/TREK.
Large language models (LLMs) excel at many language understanding tasks but struggle to reason over knowledge that evolves. To address this, recent work has explored augmenting LLMs with knowledge graphs (KGs) to provide structured, up-to-date information. However, many existing approaches assume a static snapshot of the KG and overlook the temporal dynamics and factual inconsistencies inherent in real-world data. To address the challenge of reasoning over temporally shifting knowledge, we propose EvoReasoner, a temporal-aware multi-hop reasoning algorithm that performs global-local entity grounding, multi-route decomposition, and temporally grounded scoring. To ensure that the underlying KG remains accurate and up-to-date, we introduce EvoKG, a noise-tolerant KG evolution module that incrementally updates the KG from unstructured documents through confidence-based contradiction resolution and temporal trend tracking. We evaluate our approach on temporal QA benchmarks and a novel end-to-end setting where the KG is dynamically updated from raw documents. Our method outperforms both prompting-based and KG-enhanced baselines, effectively narrowing the gap between small and large LLMs on dynamic question answering. Notably, an 8B-parameter model using our approach matches the performance of a 671B model prompted seven months later. These results highlight the importance of combining temporal reasoning with KG evolution for robust and up-to-date LLM performance. Our code is publicly available at github.com/junhongmit/TREK.
Ontology for Products
Abstract
We are developing infrastructure to support researchers in mapping data related to the peripheral nervous system and other physiological systems, with an emphasis on their relevance to the organs under investigation. The nervous system, a complex network of nerves and ganglia, plays a critical role in coordinating and transmitting signals throughout the body. To aid in this, we have created ApiNATOMY, a framework for the topological and semantic representation of multiscale physiological circuit maps. ApiNATOMY integrates a Knowledge Representation (KR) model and a suite of Knowledge Management (KM) tools. The KR model enables physiology experts to easily capture interactions between anatomical entities, while the KM tools help modelers convert high-level abstractions into detailed models of physiological processes, which can be integrated with external ontologies and knowledge graphs.
We are developing infrastructure to support researchers in mapping data related to the peripheral nervous system and other physiological systems, with an emphasis on their relevance to the organs under investigation. The nervous system, a complex network of nerves and ganglia, plays a critical role in coordinating and transmitting signals throughout the body. To aid in this, we have created ApiNATOMY, a framework for the topological and semantic representation of multiscale physiological circuit maps. ApiNATOMY integrates a Knowledge Representation (KR) model and a suite of Knowledge Management (KM) tools. The KR model enables physiology experts to easily capture interactions between anatomical entities, while the KM tools help modelers convert high-level abstractions into detailed models of physiological processes, which can be integrated with external ontologies and knowledge graphs.
MECE Mutually Exclusive, Collectively Exhaustive.Knowledge Management
Abstract
Your company's CEO is retiring. You search for a successor. You can promote an employee from the company familiar with the company's operations, or recruit an external professional manager. Who should you prefer? It has not been clear how to address this question, the "subject matter expertise vs. professional manager debate", quantitatively and objectively. We note that a company's success depends on long sequences of interdependent decisions, with often-opposing recommendations of diverse board members. To model this task in a controlled environment, we utilize chess - a complex, sequential game with interdependent decisions which allows for quantitative analysis of performance and expertise (since the states, actions and game outcomes are well-defined). The availability of chess engines differing in style and expertise, allows scalable experimentation. We considered a team of (computer) chess players. At each turn, team members recommend a move and a manager chooses a recommendation. We compared the performance of two manager types. For manager as "subject matter expert", we used another (computer) chess player that assesses the recommendations of the team members based on its own chess expertise. We examined the performance of such managers at different strength levels. To model a "professional manager", we used Reinforcement Learning (RL) to train a network that identifies the board positions in which different team members have relative advantage, without any pretraining in chess. We further examined this network to see if any chess knowledge is acquired implicitly. We found that subject matter expertise beyond a minimal threshold does not significantly contribute to team synergy. Moreover, performance of a RL-trained "professional" manager significantly exceeds that of even the best "expert" managers, while acquiring only limited understanding of chess.
Your company's CEO is retiring. You search for a successor. You can promote an employee from the company familiar with the company's operations, or recruit an external professional manager. Who should you prefer? It has not been clear how to address this question, the "subject matter expertise vs. professional manager debate", quantitatively and objectively. We note that a company's success depends on long sequences of interdependent decisions, with often-opposing recommendations of diverse board members. To model this task in a controlled environment, we utilize chess - a complex, sequential game with interdependent decisions which allows for quantitative analysis of performance and expertise (since the states, actions and game outcomes are well-defined). The availability of chess engines differing in style and expertise, allows scalable experimentation. We considered a team of (computer) chess players. At each turn, team members recommend a move and a manager chooses a recommendation. We compared the performance of two manager types. For manager as "subject matter expert", we used another (computer) chess player that assesses the recommendations of the team members based on its own chess expertise. We examined the performance of such managers at different strength levels. To model a "professional manager", we used Reinforcement Learning (RL) to train a network that identifies the board positions in which different team members have relative advantage, without any pretraining in chess. We further examined this network to see if any chess knowledge is acquired implicitly. We found that subject matter expertise beyond a minimal threshold does not significantly contribute to team synergy. Moreover, performance of a RL-trained "professional" manager significantly exceeds that of even the best "expert" managers, while acquiring only limited understanding of chess.
Abstract
When AI systems allow human-like communication, they elicit increasingly complex relational responses. Knowledge workers face a particular challenge: They approach these systems as tools while interacting with them in ways that resemble human social interaction. To understand the relational contexts that arise when humans engage with anthropomorphic conversational agents, we need to expand existing human-computer interaction frameworks. Through three workshops with qualitative researchers, we found that the fundamental ontological and relational ambiguities inherent in anthropomorphic conversational agents make it difficult for individuals to maintain consistent relational stances toward them. Our findings indicate that people's articulated positioning toward such agents often differs from the relational dynamics that occur during interactions. We propose the concept of relational dissonance to help researchers, designers, and policymakers recognize the resulting tensions in the development, deployment, and governance of anthropomorphic conversational agents and address the need for relational transparency.
When AI systems allow human-like communication, they elicit increasingly complex relational responses. Knowledge workers face a particular challenge: They approach these systems as tools while interacting with them in ways that resemble human social interaction. To understand the relational contexts that arise when humans engage with anthropomorphic conversational agents, we need to expand existing human-computer interaction frameworks. Through three workshops with qualitative researchers, we found that the fundamental ontological and relational ambiguities inherent in anthropomorphic conversational agents make it difficult for individuals to maintain consistent relational stances toward them. Our findings indicate that people's articulated positioning toward such agents often differs from the relational dynamics that occur during interactions. We propose the concept of relational dissonance to help researchers, designers, and policymakers recognize the resulting tensions in the development, deployment, and governance of anthropomorphic conversational agents and address the need for relational transparency.
Interests not found
We did not find any papers that match the below interests.
Try other terms also consider if the content exists in arxiv.org.
- Taxonomy of Products
You can edit or add more interests any time.
Help us improve your experience!
This project is on its early stages your feedback can be pivotal on the future of the project.
Let us know what you think about this week's papers and suggestions!
Give Feedback